A TypeScript implementation of a simple MCP server that exposes datetime information to agentic systems and chat REPLs
Nothing to run from here
Convocore is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
61
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Build, test and manage customer-facing AI voice and chat agents (web, WhatsApp, phone) from chat.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http convocore-mcp https://mcp.convocore.app/mcp
# 2 — ask your agent for something these tools do
# integrate_website_widget, generate_widget_css, create_agent and 58 more
Convocore costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MOAll 2 servers
moe032 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Its publisher asks you to sign in with OAuth: run /mcp in Claude Code and pick this server, and it opens a browser for that once.
claude mcp add --scope user --transport http convocore-mcp https://mcp.convocore.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — the only sign-in is its publisher’s own, with OAuth.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
61 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Generate a ready-to-paste website embed snippet for a Convocore agent. Fetches the agent ID and fills in region automatically. Use when the user asks to add the chatbot to their site, embed the widget, or get the script tag. Modes: popup-bottom-right (default), popup-bottom-left, full-width…
No parameter schema on file.
Load the full Convocore (vg) chat-widget CSS styling guide as a system message — includes the cascade rule, the complete .vg-* class/id map, hard constraints, the NextUI/Tailwind color system, and selector recipes. Use this whenever you want the assistant to generate or refine CSS for the chat…
No parameter schema on file.
Create a Convocore agent (advanced/raw). Prefer create_agent_from_template for website/branded agents. Always node-based: enableNodes is forced true; put the main prompt in systemPrompt (or nodes[0].instructions) — do NOT use vg_instructions (API rejects that field). Default chat model is always…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | The title of the agent |
| description | string | no | A brief description of the agent |
| theme | string | no | Visual theme (e.g., blue-light, custom-blue-dark) |
| disabled | boolean | no | Whether the agent should be disabled |
| light | boolean | no | Enable light mode (no chat history retention for privacy) |
| enableVertex | boolean | no | Enable Vertex AI for the agent |
| autoOpenWidget | boolean | no | Auto-open widget when agent loads |
| systemPrompt | string | no | Main behavior prompt → written to nodes[0].instructions (enableNodes always true). |
| voiceConfig | no | — | |
| nodes | array | no | Optional nodes. If omitted with systemPrompt, MCP creates the start node. Main prompt MUST be nodes[0].instructions. |
| allowRemoveTools | boolean | no | Default false: toolsIds in a nodes patch are unioned with the live list. Set true only to intentionally remove tools. |
| additionalConfig | no | — |
PRIMARY way to create chat+voice agents. Workspace is resolved internally from MCP configuration/workspace secret context (no workspaceId input). Uses strict template invariants: agentPlatform=vg, enableNodes=true, vg_enableUIEngine=true, vg_enableUIEngineForms=true + form notify, default…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | no | Agent title |
| description | string | no | Short description |
| systemPrompt | string | no | Main chat / node instructions → nodes[0].instructions only. Do not send vg_instructions. |
| voicePrompt | string | no | Optional Gemini Live systemInstruction text. If omitted, systemPrompt is used for voice as well. |
| voiceConfig | no | Full voice configuration. speechGen.provider MUST be google-live or ultravox. Use search_voices on those providers only. | |
| primaryColor | string | no | Hex brand colour, e.g. #226D7A (from scrape_url colour list). |
| themeType | string | no | Widget theme (default light unless user wants dark) |
| widgetImageUrl | string | no | Widget assistant avatar/logo URL (favicon from scrape_url is ideal). |
| image | string | no | Backward-compatible alias for widgetImageUrl. |
| defaultLanguage | string | no | Default language for the agent. Must be a single language code/name (never "multilingual"). Default: "en". |
| language | string | no | Backward-compatible alias for defaultLanguage. |
| proactiveMessage | string | no | Widget greeting bubble |
| sourceUrl | string | no | Optional — MCP waits for scrape (for KB / context). Not required to create the agent. |
| url | string | no | Backward-compatible alias for sourceUrl. |
| roundedImageURL | string | no | Backward-compatible alias for image. |
| template | string | no | Backward-compatible field currently ignored. |
| createKbUrlDoc | boolean | no | If true with sourceUrl, attach URL KB after create (errors are non-fatal). |
| ownerNotifyEmails | array | no | Sales/owner emails. Used for form notify AND funnelConfig.notificationRules. Required for email alerts on hot leads. Do NOT create a custom HTTP webhook for this. |
| appendStandardPromptClauses | boolean | no | Default true: appends anti-repetition, lead-capture, knowledge-source, web-search, pricing and photo clauses to systemPrompt. Set false to store systemPrompt exactly as given (use for non-sales agents |
| attachWebSearchTool | boolean | no | Default true: attaches built-in web-search to the start node. Set false for agents that must not search the web. |
Retrieve details of a specific Convocore agent. Main prompt is always nodes[0].instructions (enableNodes is true for agents created via this MCP). Legacy vg_instructions only if nodes are absent on a very old agent. ownerID is the workspaceId and is read-only. Response includes prototypeUrl /…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The unique identifier of the agent |
Update an existing Convocore agent (PATCH). For large prompt edits prefer patch_agent_prompt. Main prompt: use systemPrompt → start node instructions. NEVER send vg_instructions or vg_systemPrompt. Do NOT pass nodes[] unless you are changing nodes — omit it for title/UI/funnel/model updates.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The unique identifier of the agent to update |
| title | string | no | Updated title |
| description | string | no | Updated description |
| theme | string | no | Updated theme |
| disabled | boolean | no | Updated disabled status |
| light | boolean | no | Updated light mode setting |
| enableVertex | boolean | no | Updated Vertex AI setting |
| autoOpenWidget | boolean | no | Updated auto-open widget setting |
| systemPrompt | string | no | Replace main prompt → nodes[0].instructions (enableNodes forced true). Prefer patch_agent_prompt for surgical edits. |
| voiceConfig | no | — | |
| nodes | array | no | Node patch. MCP merges onto the current graph by node id so partial updates (e.g. toolsIds) cannot blank nodes[0].instructions. Prefer systemPrompt for prompt writes. |
| additionalConfig | no | Every other agent field the API accepts, typed from the main agent schema. Send only what changes: nested objects (nodesSettings, vg_kb_llm, ui…) are deep-merged into the current value, so existing se |
Performs string replacements in the start-node prompt (or proactiveMessage / customCSS). USE THIS instead of update_agent when the prompt is large and you only need to change a specific section. If get_agent returns empty instructions, this tool REFUSES a surgical patch — it will NOT replace the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID whose prompt/text field to patch |
| old_string | string | no | Text to find. Copy from get_agent. If the field is empty, this tool refuses a surgical patch — only omit old_string when installing a FULL prompt. |
| new_string | string | yes | Replacement text for the matched span. Use an empty string to delete the matched text. |
| replace_all | boolean | no | If false (default), fails when old_string matches more than once. If true, replaces every occurrence. |
| target | string | no | Field to patch. auto / vg_instructions / vg_systemPrompt all write nodes[0].instructions. customCSS patches widget CSS surgically. |
| sync_mirrors | boolean | no | When true, also apply the same replace to other writable prompt copies. Default false. vg_instructions / vg_systemPrompt are never written. |
Delete a Convocore agent permanently
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The unique identifier of the agent to delete |
List accessible agents. Default mode="compact" returns only short fields (id, title, description, theme, flags, timestamps) so responses stay token-cheap — use this to find recent agents. mode="full" returns complete agent documents (nodes/prompts/voice/etc.) and is heavy; prefer get_agent for one…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | compact (default): short summary fields only. full: entire agent objects from the API (very large). |
| limit | number | no | Max agents when supported. Compact defaults to 25. Full mode: always pass a small limit. |
Search/filter Convocore agents. Default mode=compact (short fields only). Use mode=full only when you need complete agent docs. Prefer list_agents (compact) for recent agents without a query.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | — |
| search | string | no | Search query to find agents |
| page | number | no | Page number (default: 1) |
| limit | number | no | Results per page (default: 50) |
| sortBy | string | no | Sort by: newest, oldest, alphabetical (default: newest) |
| starredOnly | boolean | no | Show only starred agents (default: false) |
Export an agent template for backup or migration. For import/export, rely on these dedicated OpenAPI routes instead of trying to manually construct the template shape.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID to export |
Import an agent from a template produced by export_agent / the OpenAPI export-template route. The template shape is complex; do not invent it manually unless the user provides an exact exported object.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentTemplate | object | yes | Agent template object from export_agent / export-template. Pass the exported template object through; do not manually invent nested template fields. |
| agentName | string | yes | Name for the imported agent |
| fromAgentId | string | no | Optional source agent ID to preserve import lineage/context when the backend supports it. |
Get agent usage statistics and credits consumed
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID to get usage for |
| range | object | no | Optional date range for usage stats |
List an agent's conversations, newest first, up to 20 per page. Each row has the conversation ID, time, the stored summary (if one was generated), the user and the channel; message bodies are not included (get_conversation returns them). mode=full returns the complete list rows. Page with the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | — |
| agentId | string | yes | The agent ID to list conversations for |
| cursor | string | no | Opaque cursor from previous response nextCursor. Required to paginate past the first page. |
| limit | number | no | Results per page (default: 20, max: 20) |
| page | number | no | Legacy. Only page=1 without cursor. Prefer cursor / nextCursor / hasMore. |
Create a new conversation for an agent
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| conversation | object | yes | Conversation object (minimum: { ts: timestamp }) |
Get details of a single conversation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoId | string | yes | The conversation ID |
Patch fields on the light conversation document. This does NOT replace the stored turn/message history. To replace transcript turns, use update_conversation_messages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoId | string | yes | The conversation ID |
| conversation | object | yes | Conversation fields to update |
Replace the stored message turn history for a conversation using PATCH /agents/{agentId}/convos/{convoId}/messages. This overwrites voiceglow/{agentId}/convos/{convoId}/convo/JSON_STRING with the provided turns array. Set updateConversationMetadata=true (default) to also refresh messagesNum,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID. |
| convoId | string | yes | The conversation ID. |
| turns | array | yes | Complete replacement turn history. Each turn requires from + messages. This array becomes the stored transcript history. |
| lgMessages | array | no | Optional LangGraph/langchain message array passthrough. |
| updateConversationMetadata | boolean | no | Default true. Refreshes messagesNum, lastMessage, firstMessageTS, lastMessageTS, and lastModified on the light conversation document. |
| confirmReplace | boolean | yes | Must be true because this replaces the stored conversation message history. |
Delete a conversation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoId | string | yes | The conversation ID |
Export conversations for an agent (Postgres mirror). Requires a paid workspace (hasEverPaid === true); billed against monthly export quota. Supports cursor pagination via cursor/nextCursor/hasMore, or selected mode via convoIds. Formats: json|csv.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| format | string | no | Export format (default: json) |
| limit | number | no | Max conversations in this export page |
| sort | string | no | Sort order (API-defined) |
| fromTs | number | no | Unix timestamp lower bound (inclusive) |
| toTs | number | no | Unix timestamp upper bound (inclusive) |
| cursor | string | no | Opaque cursor from previous export nextCursor |
| convoIds | array | no | If set, export only these conversation IDs |
Export a single conversation. Requires a paid workspace (hasEverPaid === true); billed against monthly export quota.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoId | string | yes | The conversation ID |
| format | string | no | Export format (default: json) |
Assign a conversation to a user for manual delegation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoId | string | yes | The conversation ID |
| assignToUserId | string | yes | User ID to assign to |
| delegatedBy | string | no | Optional: ID of user delegating |
Fetch lean summaries for many conversation IDs in one call (fan-out GETs with concurrency). Returns {ID, summary, ts, capturedVariables, userName, origin} per convo. Max 50 IDs per call — chunk larger audits. Workflow: list_conversations with cursor to collect IDs, then this tool (do NOT loop…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| convoIds | array | yes | Conversation IDs (1–50) |
MCP-side filter over conversations (NOT a SQL analytics API). Cursor-pages list_conversations then bulk-gets details when filters need summary/capturedVariables/userName. Bounded by maxScan (default 200). Use for audits like summaryContains or capturedVariableExists. True server-side filters…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| limit | number | no | Max matches (default 50, max 100) |
| maxScan | number | no | Max list rows to scan (default 200, max 500) |
| origin | string | no | Exact origin match |
| tsFrom | number | no | Unix ts lower bound |
| tsTo | number | no | Unix ts upper bound |
| capturedVariableExists | string | no | Require this capturedVariables key |
| capturedVariableEquals | object | no | Require capturedVariables[key] === value |
| summaryContains | string | no | Case-insensitive summary substring |
| hasUserName | boolean | no | Require / exclude userName |
| hasNotes | boolean | no | Require / exclude human review notes |
| noteContains | string | no | Case-insensitive substring in any review note |
Fetch usage/credits for many agents in one call (fan-out). Max 20 agentIds. Optional shared date range.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentIds | array | yes | Agent IDs (1–20) |
| range | object | no | Optional date range |
Fetch many KB documents in one call (fan-out). Max 30 docIds. Default returns compact metadata + chunksPreview; set includeContent=true for full bodies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| docIds | array | yes | KB document IDs (1–30) |
| includeContent | boolean | no | Include full chunks/content (default false) |
PREFERRED for adding many website pages to an agent KB. Pass up to 50 URLs; the Convocore KB router scrapes them (scrapeContent=true). Do NOT web-fetch/scrape_url then paste content into create_kb_doc — that is slow and duplicates work. mode=per_url (default): one KB doc per URL. mode=batch: one…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| urls | array | yes | Page URLs to ingest via KB router (max 50) |
| mode | string | no | per_url (default) or batch (single source with all urls) |
| name | string | no | batch: doc name. per_url: optional name prefix |
| tags | array | no | — |
| refreshRate | string | no | Auto re-crawl (API: 3d | 7d | never). Default never. |
| scrapeContent | boolean | no | KB router scrape (default true) |
| skipExisting | boolean | no | Skip URLs already on the agent KB (default true) |
| metadata | object | no | — |
Add one knowledge base source (VG agents). For many page URLs use create_kb_from_urls instead. For websites: sourceType=url with urls[] + scrapeContent=true (KB router scrapes). For whole-site: sourceType=sitemap + sitemapUrl + maxPages + scrapeContent=true. sourceType=doc only for raw text you…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| name | string | yes | Document name |
| sourceType | string | yes | doc = text; url = KB router scrape urls[]; sitemap = crawl sitemap |
| content | string | no | Document content (required for sourceType: doc) |
| metadata | object | no | Additional metadata |
| tags | array | no | Tags for organization |
| refreshRate | string | no | Auto re-crawl for URL/sitemap (API: 3d | 7d | never). Default never. |
| urls | array | no | Array of URLs (for sourceType: url). Prefer create_kb_from_urls for many pages. |
| sitemapUrl | string | no | Sitemap URL (for sourceType: sitemap) |
| maxPages | number | no | Max pages from sitemap |
| scrapeContent | boolean | no | Let KB router scrape URLs/sitemap (set true for url/sitemap) |
List knowledge base documents for an agent. Default mode=compact (id/name/status/urls — NO content bodies). Use mode=full only if you need every list field; prefer get_kb_doc for one document body.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | — |
| agentId | string | yes | The agent ID |
| page | number | no | Page number (default: 1) |
| pageSize | number | no | Results per page (default: 20) |
Get a single knowledge base document
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| docId | string | yes | The document ID |
Update a knowledge base document (VG agents only). For large document bodies prefer patch_kb_doc (Cursor-style exact old_string→new_string) instead of rewriting the entire content field.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| docId | string | yes | The document ID |
| name | string | no | Updated name |
| content | string | no | Updated content |
| metadata | object | no | Updated metadata |
| tags | array | no | Updated tags |
| refreshRate | string | no | Updated refresh rate (API: 3d | 7d | never) |
| url | string | no | Updated URL |
Performs string replacements in a knowledge-base document — same idea as Cursor StrReplace for files. USE THIS instead of update_kb_doc when the document body is large and you only need to change a specific section. Workflow: get_kb_doc → copy the span into old_string (include enough surrounding…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| docId | string | yes | The KB document ID |
| old_string | string | yes | Text to find in the KB field. Prefer an exact copy from get_kb_doc; minor whitespace/line-ending drift is tolerated. Include surrounding context so the match is unique unless replace_all is true. |
| new_string | string | yes | Replacement text for the matched span. Use an empty string to delete the matched text. |
| replace_all | boolean | no | If false (default), fails when old_string matches more than once. If true, replaces every occurrence. |
| field | string | no | Which KB field to patch. Default content (document body). |
Delete a knowledge base document (VG agents only)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
| docId | string | yes | The document ID |
Get knowledge base statistics for an agent (VG agents only)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID |
Validate and/or scrape HTTP(S) URLs. DEFAULT mode=check: fast ping of one or many links/images (up to 20) — returns status (200/301/404/etc), ok, content-type, final URL after redirects. Use this to verify widget images, logos, CDN assets, booking links, or any URL before putting it on an agent.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | Single URL (optional if urls is set) |
| urls | array | no | URLs to check (preferred for validating multiple image/page links) |
| mode | string | no | check = HTTP status ping (default). scrape = full page scrape (one URL only). |
| useProxy | boolean | no | mode=scrape only. Default false. true = expensive proxy scrape (~60 credits/page). ONLY after normal scrape failed AND user confirmed the extra credit cost. |
| confirmExpensiveProxy | boolean | no | Must be true together with useProxy=true. Confirms the user approved burning extra Convocore workspace credits for proxy scraping. |
MUST CALL whenever the user asks to deploy/embed/add their agent to a website, get the widget script, iframe code, popup chat bubble, or 'where is the code'. Returns a ready-to-paste HTML snippet with the real agent ID and region filled in (popup, full-width inline, modal, or React voice-only…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The Convocore agent ID to embed. |
| mode | string | no | popup-bottom-right (default bubble), popup-bottom-left, full-width (sized div), modal (center overlay), voice-react (Next.js @tixae-labs/web-sdk). |
| containerWidth | string | no | full-width only, e.g. "500px". |
| containerHeight | string | no | full-width only, e.g. "500px". |
MUST CALL FIRST whenever the user asks to style/restyle/theme the Convocore (vg) chat widget — e.g. 'change the icons to black', 'make the header purple', 'recolor the send button', 'theme the widget dark', 'change the user bubble color', 'restyle the proactive teaser'. Returns the FULL…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | no | Optional. If provided, the agent's current customCSS is appended to the guide so you can extend/refine the existing rules instead of duplicating them. |
Read the agent's current customCSS field (the per-agent CSS override applied to the chat widget). Returns the raw CSS string (empty string if none set). Use this before editing so you can produce a merged result for update_agent_custom_css.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID whose customCSS field you want to read |
Cheap probe of a file (path / url / base64). Returns kind, mime, size, page count (PDF), sheet names (XLSX), line count (text), or pixel dimensions (image), plus an estimated token cost. ALWAYS call this first on anything larger than a few KB — use it to decide which read_* tool to call and which…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | Local file path. Mutually exclusive with url/data. |
| url | string | no | https:// URL. Mutually exclusive with path/data. |
| data | string | no | Base64 file contents. Mutually exclusive with path/url. |
| mimeType | string | no | Optional MIME hint (mostly for data mode). |
Read a plain-text file (.txt, .md, .json, .csv, .yaml, .log, code, etc.) from path / url / base64. Returns UTF-8 text plus a truncation flag and token estimate. Honors an optional maxBytes cap. For .docx use read_docx, for .pdf use read_pdf, for .xlsx use read_spreadsheet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| maxBytes | number | no | Optional cap on bytes to read. |
Extract text from a PDF (path / url / base64). Page-aware: pass pages as a string range like "1-3,5,7-9" or an explicit array to read only the pages you need. Output is split per page with --- page N --- headers. Auto-truncates if the result would exceed the per-call token budget. Always…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| pages | no | Optional page selection. Defaults to all pages. |
Extract text from a .docx Word document (path / url / base64). Set asMarkdown=true to preserve headings, lists, links and bold/italic. Legacy .doc is NOT supported — convert to .docx first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| asMarkdown | boolean | no | Return markdown instead of plain text. Default: false. |
Read an Excel (.xlsx / .xlsm / .xls) or CSV file. Two-step pattern: (1) call WITHOUT sheet to list sheet names, (2) call again with sheet to read that sheet. Optional A1-style range (e.g. "A1:D50") and format ('markdown' default, or 'csv' / 'json'). headerRow=true (default) treats row 1 as…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| sheet | no | Sheet name or zero-based index. Omit to just list sheets. | |
| range | string | no | Optional A1 range like "A1:D50". |
| format | string | no | Output format. Default: markdown. |
| headerRow | boolean | no | For json: treat row 1 as headers (default: true). |
| maxRows | number | no | Cap on rows returned (default: 1000, max: 50000). |
Load an image (PNG / JPEG / WebP / GIF / SVG / TIFF / BMP / HEIC) from path / url / base64 and return it as a vision-ready MCP image content block so YOU can see the pixels. REQUIRED after scraping a website: call this with url= on every high-value product/room/treatment/team photo, then write…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| maxDimension | number | no | Max width/height in pixels (default: 2048, range: 64-4096). Larger images are downscaled. |
End-to-end shortcut: read any supported file (PDF / DOCX / XLSX / CSV / TXT / MD / JSON / HTML) and create a Knowledge Base document on the target agent in one call. The file is parsed locally to text/markdown and pushed to the agent's KB via create_kb_doc with sourceType='doc'. Use pages for…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | Target agent ID. |
| path | string | no | — |
| url | string | no | — |
| data | string | no | — |
| mimeType | string | no | — |
| name | string | no | KB document name. Defaults to the source filename. |
| tags | array | no | Optional tags. |
| pages | no | PDF only: page selection. | |
| sheet | no | Spreadsheet only: which sheet to ingest (default: first). | |
| asMarkdown | boolean | no | Prefer markdown output (default: true). |
Overwrite the agent's customCSS field with new CSS that styles the chat widget. IMPORTANT: this REPLACES the existing customCSS value — always pass the FULL merged CSS (existing + your new rules), not just the delta. Workflow: (1) call get_widget_css_styling_guide to load selectors + rules, (2)…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The agent ID whose customCSS field you want to overwrite |
| customCSS | string | yes | The full CSS to write to the agent.customCSS field. REPLACES the existing value entirely. Use an empty string to clear. |
Pause for the given number of seconds and then return. Useful when you need to wait between actions (e.g. polling a job, rate-limiting, giving an external system time to settle). Range: 0–300 seconds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seconds | number | yes | How long to wait, in seconds (0–300). |
Execute a shell command on the host machine where the MCP server is running and return stdout, stderr, and the exit code. Runs through the platform default shell (cmd.exe on Windows, /bin/sh on Unix). Use for simple system tasks like checking versions, listing files, or running short scripts.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| command | string | yes | The shell command to execute (e.g. "node --version" or "ls -la"). |
| cwd | string | no | Optional working directory. Defaults to the MCP server cwd. |
| timeoutSeconds | number | no | Kill the process after this many seconds. Default 30, max 600. |
List every TTS voice provider Convocore supports (elevenlabs, deepgram, cartesia, rime-ai, openai, google-cloud, google-live (Gemini Live), ultravox, minimax, playht, azure). For each provider returns the workspace secret-key name (e.g. ELEVENLABS_API_KEY) and a requiresWorkspaceApiKey flag…
No parameter schema on file.
List the available TTS models for a given provider (e.g. "aura-2" for Deepgram, "eleven_multilingual_v2" for ElevenLabs). Use the returned modelId values with search_voices / list_provider_voices to filter the catalog. Read-only — does NOT consume credits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | Provider slug, e.g. "elevenlabs", "deepgram", "cartesia", "openai", "google-cloud", "azure". |
Unified voice search across one or more TTS providers. Every result is normalized to { voiceId, name, provider, previewUrl, filters: { accent, gender, useCase, language } }. Use this when the user asks for a voice by gender / language / accent without caring which provider. Read-only — does NOT…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| language | string | no | Inclusive match: "en" matches "en-US", "en-GB", "English". Use BCP-47 codes or English names. |
| gender | string | no | male / female / neutral. Aliases m / f / masculine / feminine accepted. |
| accent | string | no | Substring match, e.g. "american", "british". |
| modelId | string | no | Filter to a specific TTS model id when relevant. |
| providers | string | no | Comma-separated provider slugs to limit the search (e.g. "elevenlabs,cartesia"). Omit for all providers. |
| limit | number | no | Page size, 1–500. Default 100. |
| offset | number | no | Pagination offset. Default 0. |
Browse the voice catalog for ONE specific provider with the same filter params as search_voices. Use when the user has already chosen a provider (e.g. "show me ElevenLabs male British voices"). Read-only — does NOT consume credits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | Provider slug, e.g. "elevenlabs". |
| language | string | no | Language filter (e.g. "en", "de"). |
| gender | string | no | male / female / neutral. |
| accent | string | no | Substring match (e.g. "american"). |
| modelId | string | no | Filter to a specific TTS model id. |
| limit | number | no | Page size, 1–500. Default 100. |
| offset | number | no | Pagination offset. Default 0. |
Fetch full metadata + a preview MP3 URL for a single voice. Use after the user picks one from search_voices / list_provider_voices, or when they paste a voice ID. Read-only — does NOT consume credits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | Provider slug, e.g. "elevenlabs". |
| voiceId | string | yes | Provider-specific voice ID (e.g. "21m00Tcm4TlvDq8ikWAM" for ElevenLabs Rachel). |
Import a Twilio SMS/voice number you already own into the workspace (uses your Twilio account credentials). This is NOT a WhatsApp Cloud API connection; do not use it for waNumbers/Meta WhatsApp. Pass the full request body for /utils/import-twilio-number as an object — typically includes your…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payload | object | yes | Full request body object for /utils/import-twilio-number. |
Release (delete) a Twilio SMS/voice number from the workspace. This does not remove WhatsApp Cloud API waNumbers. Pass the full request body for /utils/twilio/release-number as an object — typically includes phoneNumber or phoneNumberSid.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payload | object | yes | Full request body object for /utils/twilio/release-number. |
Repair / re-sync the Twilio SMS/voice webhook configuration for a number (useful when call/SMS routing breaks). This does not check WhatsApp Cloud API health. Pass the full request body for /utils/twilio/check-number as an object — typically includes phoneNumber or phoneNumberSid.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payload | object | yes | Full request body object for /utils/twilio/check-number. |
Assign a Twilio number to an agent for SMS handling. This is SMS only; WhatsApp routing uses waNumbers/{phoneId}, origin "whatsapp", and Meta Cloud API. Pass the full request body for /utils/twilio/sync-sms as an object — typically includes phoneNumber (or sid) and agentId.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payload | object | yes | Full request body object for /utils/twilio/sync-sms. |
Send one test message to one of the user's Convocore agents and return the agent's reply, exactly as a customer chatting with it would see it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentId | string | yes | The ID of the agent to interact with. |
| convoId | string | yes | Conversation ID. Reuse across turns to keep history; use a fresh ID to start a new conversation. |
| prompt | string | no | User message. Special values: "start" (initial greeting), "@cancel:<reason>", "@rewind:<nodeId>". |
| bucket | string | no | Region bucket. Auto-derived from CONVOCORE_API_REGION when omitted (eu-gcp -> "voiceglow-eu", na-gcp -> "(default)"). |
| sessionId | string | no | Optional session id; defaults to convoId server-side. |
| messageType | string | no | Type of input. Use "visual" together with visualPayload for images. |
| visualPayload | object | no | Image/visual content for messageType: "visual" turns. |
| replyTo | object | no | Reply context when the user is replying to a previous message. |
| lightConvoData | object | no | Per-conversation user/context metadata (userName, userEmail, userPhone, origin, capturedVariables, ...). Surfaced to the agent system prompt where supported. |
| agentData | object | no | Optional agent override. When provided with at least an ID, the server skips loading the agent doc from Firestore. |
| workspaceData | object | no | Optional workspace override. |
| turnsHistory | array | no | Optional override of conversation turns. When set, the server uses this instead of fetching from Firestore. |
| disableUiEngine | boolean | no | Disable UI-engine JSON output for this turn. |
| disableRecordHistory | boolean | no | Skip persisting this turn to Firestore. |
| v2 | boolean | no | Force routing to the v2 (node-based) handler. |
| isTest | boolean | no | Marks the turn as a test interaction. |
| isLLMStudio | boolean | no | Marks the turn as originating from LLM Studio. |
| kbPreview | boolean | no | Knowledge-base preview mode (skips node routing). |
| agentProfileId | string | no | Internal profile id (e.g. agency_plan_builder_v1). |
| toolTest | object | no | Run a single tool in test mode. |
Return the FULL Convocore UI Engine schema (the structured message format agents emit when vg_enableUIEngine: true). ALWAYS CALL THIS FIRST when: (a) testing a UI-Engine-enabled agent via interact_with_agent and you need to validate the output, OR (b) creating / updating an agent that should…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| section | string | no | Which slice of the spec to return. Default: "all". |
| messageType | string | no | When set, return only the schema for this message type (overrides section). Use when you only need one shape. |
Return static Convocore channel-integration schema guidance for MCP clients. Use this before configuring or explaining WhatsApp, Facebook Messenger, Instagram, or SMS routing. It clarifies canonical storage locations, safe update fields, read-only/system-managed fields, credential masking,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| section | string | no | Which section to return. "whatsapp" covers waNumbers, coexistence, AI reply controls, voice settings, safe patch matrix, and recommended tools. "metaPages" covers Facebook Messenger/Instagram page doc |
Return Convocore pricing information so the assistant can quote plans, add-ons, voice/chat cost rules of thumb, credit conversions, and per-model token prices to the user. Use section to narrow the response: "plans", "add_ons", "credits", "rules_of_thumb", "models", "voice_providers", "faq", or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| section | string | no | Which slice of pricing to return. Default: "all". |
| modelFilter | string | no | Optional substring match (model name or provider) when section="models". E.g. "gpt", "claude", "gemini". |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Convocore or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 2.6.16.
2.6.16
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Convocore can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.