Validate Formhaus form definitions and simulate multi-step paths against the real engine.
Nothing to run from here
Famulor 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.
96/100
trust score
8
downloads a day
local
runs on your machine
113
downloads in 30d
What it does
MCP Server for Famulor Voice Agent Platform - AI-powered phone calling and voice assistant management
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user famulor-mcp '--' npx -y famulor-mcp
# 2 — ask your agent for something these tools do
# get_me, get_assistants, get_outbound_assistants and 72 more
Famulor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BEAll 1 server
bekservice1 server
1 category
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. This one runs on your machine: your client starts Famulor as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user famulor-mcp '--' npx -y famulor-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
75 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.
Get the authenticated Famulor user profile, including total balance.
No parameter schema on file.
List all AI assistants on the Famulor account (paginated). Returns the assistant configurations including their fixed variable names.
No parameter schema on file.
List all outbound-capable assistants.
No parameter schema on file.
List phone numbers eligible to be attached to an assistant (filter by inbound/outbound).
No parameter schema on file.
List available LLM / multimodal / dualplex model IDs.
No parameter schema on file.
List voices compatible with a given engine mode and optional language.
No parameter schema on file.
List all supported assistant languages.
No parameter schema on file.
List custom TTS providers selectable on an assistant.
No parameter schema on file.
List custom STT providers selectable on a pipeline assistant.
No parameter schema on file.
Create a new AI assistant. Required: name, voice_id, language_id, type, mode, timezone, initial_message, system_prompt, and either llm_model_id (pipeline) or multimodal_model_id (multimodal/dualplex). For multimodal/dualplex, knowledgebase_mode must be
No parameter schema on file.
Update an existing assistant (partial). Only the fields you send are changed.
No parameter schema on file.
Permanently delete an assistant. Cannot be undone.
No parameter schema on file.
Enable inbound-call webhook notifications for an assistant.
No parameter schema on file.
Disable inbound-call webhook notifications.
No parameter schema on file.
Enable conversation-ended (chat) webhook for an assistant.
No parameter schema on file.
Disable conversation-ended (chat) webhook.
No parameter schema on file.
Disable the post-call webhook for an assistant.
No parameter schema on file.
Initiate an outbound AI phone call with a configured assistant.
No parameter schema on file.
Retrieve a single call by ID.
No parameter schema on file.
List calls with pagination and optional assistant filter.
No parameter schema on file.
Delete a call record. Cannot be undone.
No parameter schema on file.
List conversations across your assistants with cursor pagination and filters.
No parameter schema on file.
Get the full message history of a chat conversation by UUID.
No parameter schema on file.
Start a new chat session with an assistant (widget=paid, test=free).
No parameter schema on file.
Send a user message in an existing chat conversation and get the assistant reply.
No parameter schema on file.
Re-enable AI replies for a conversation after a human takeover.
No parameter schema on file.
Disable AI replies for a conversation so a human can take over.
No parameter schema on file.
List all outbound calling campaigns.
No parameter schema on file.
Create a new outbound campaign tied to an outbound-capable assistant.
No parameter schema on file.
Start or stop a campaign.
No parameter schema on file.
Delete a campaign. Cannot be undone.
No parameter schema on file.
List leads with pagination.
No parameter schema on file.
Create a new lead in a campaign. IMPORTANT: variable names come from the associated assistant configuration and are fixed; only their values can be supplied here.
No parameter schema on file.
Update a lead. Variables are merged with existing ones.
No parameter schema on file.
Delete a lead.
No parameter schema on file.
Send an SMS from one of your Famulor phone numbers (must be SMS-capable). Costs are deducted from your balance.
No parameter schema on file.
List mid-call tools (HTTP integrations callable by an assistant during a call).
No parameter schema on file.
Get a single mid-call tool by ID.
No parameter schema on file.
Create a new mid-call HTTP tool.
No parameter schema on file.
Update a mid-call tool. headers/schema fully replace existing values when provided.
No parameter schema on file.
Delete a mid-call tool.
No parameter schema on file.
List all knowledge bases on the account.
No parameter schema on file.
Get a knowledge base by ID.
No parameter schema on file.
Create a new knowledge base.
No parameter schema on file.
Rename or describe an existing knowledge base.
No parameter schema on file.
Delete a knowledge base permanently.
No parameter schema on file.
List documents in a knowledge base.
No parameter schema on file.
Get a single document by ID.
No parameter schema on file.
Add a website (URL-scraped) document to a knowledge base. File uploads (pdf/txt/docx) must use the Famulor dashboard or a direct multipart/form-data call.
No parameter schema on file.
Update a document name or description. Content cannot be changed.
No parameter schema on file.
Delete a document from a knowledge base.
No parameter schema on file.
List every phone number on the account (regardless of SMS or subscription status).
No parameter schema on file.
Search for purchasable phone numbers via the Famulor provider.
No parameter schema on file.
Purchase a phone number returned by search_phone_numbers (monthly subscription).
No parameter schema on file.
Update a phone number you own. Currently sets the nickname — a short human-readable label (max 50 chars) shown next to the number. Send null/empty to clear it. Granted (shared) numbers cannot be updated.
No parameter schema on file.
Release (cancel) a purchased phone number.
No parameter schema on file.
List assistant folders (paginated), each with its assistants_count. Folders group assistants, e.g. per customer or brand; an assistant belongs to at most one folder.
No parameter schema on file.
Create a folder to group assistants. Assign assistants via the folder_id field on create_assistant / update_assistant.
No parameter schema on file.
Rename a folder or change its color (partial — only sent fields change).
No parameter schema on file.
Delete a folder. Assistants inside are NOT deleted — they just become uncategorized.
No parameter schema on file.
List assistant labels (paginated), each with its assistants_count. Labels are tags; an assistant can carry multiple labels across folders.
No parameter schema on file.
Create a label to tag assistants (e.g.
No parameter schema on file.
Rename a label or change its color (partial — only sent fields change).
No parameter schema on file.
Delete a label. It is removed from all assistants it was assigned to — the assistants themselves are NOT affected.
No parameter schema on file.
List all SIP trunks on the account.
No parameter schema on file.
Get a SIP trunk by ID.
No parameter schema on file.
Provision a new SIP trunk (extension or DID number).
No parameter schema on file.
Update a SIP trunk (partial).
No parameter schema on file.
Delete a SIP trunk by phone-number ID.
No parameter schema on file.
List WhatsApp Business senders. status defaults to
No parameter schema on file.
List approved templates for a WhatsApp sender (status defaults to
No parameter schema on file.
Check whether a 24h messaging window is open for a recipient.
No parameter schema on file.
Send a WhatsApp template message (required when initiating or outside the 24h window).
No parameter schema on file.
Send a freeform WhatsApp message. Requires an open 24h session (use get_whatsapp_session_status to check).
No parameter schema on file.
Generate a context-aware AI reply for a customer message. The system keeps conversation state per customer_identifier (e.g. phone, email, CRM ID).
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- 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 Famulor 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: —
ATrust score 96 / 100
Release 0.3.1 · scanned 14 Oct 2026
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.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest88b1a8f56ddac2b578948acd707249d842dd1f0c3059571794ddeeed957bd2d3
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (75 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_me | no tags | |
| get_assistants | no tags | |
| get_outbound_assistants | no tags | |
| get_phone_numbers | no tags | |
| get_models | no tags | |
| get_voices | no tags | |
| get_languages | no tags | |
| get_synthesizer_providers | no tags | |
| get_transcriber_providers | no tags | |
| create_assistant | no tags | |
| update_assistant | no tags | |
| delete_assistant | no tags | |
| enable_assistant_inbound_webhook | external-sink | external-sink: keyword "webhook" |
| disable_assistant_inbound_webhook | external-sink | external-sink: keyword "webhook" |
| enable_assistant_conversation_ended_webhook | external-sink | external-sink: keyword "webhook" |
| disable_assistant_conversation_ended_webhook | external-sink | external-sink: keyword "webhook" |
| disable_assistant_webhook | external-sink | external-sink: keyword "webhook" |
| make_call | no tags | |
| get_call | no tags | |
| list_calls | no tags | |
| delete_call | no tags | |
| list_conversations | no tags | |
| get_conversation | no tags | |
| create_conversation | no tags | |
| send_message | external-sink | external-sink: keyword "send_message" |
| enable_conversation_ai | no tags | |
| disable_conversation_ai | no tags | |
| list_campaigns | no tags | |
| create_campaign | no tags | |
| update_campaign_status | no tags | |
| delete_campaign | no tags | |
| list_leads | no tags | |
| create_lead | no tags | |
| update_lead | no tags | |
| delete_lead | no tags | |
| send_sms | external-sink | external-sink: keyword "sms" |
| list_mid_call_tools | no tags | |
| get_mid_call_tool | no tags | |
| create_mid_call_tool | no tags | |
| update_mid_call_tool | no tags | |
| delete_mid_call_tool | no tags | |
| list_knowledgebases | no tags | |
| get_knowledgebase | no tags | |
| create_knowledgebase | no tags | |
| update_knowledgebase | no tags | |
| delete_knowledgebase | no tags | |
| list_documents | no tags | |
| get_document | no tags | |
| create_document | no tags | |
| update_document | no tags | |
| delete_document | no tags | |
| list_all_phone_numbers | no tags | |
| search_phone_numbers | no tags | |
| purchase_phone_number | no tags | |
| update_phone_number | no tags | |
| release_phone_number | no tags | |
| list_folders | no tags | |
| create_folder | no tags | |
| update_folder | no tags | |
| delete_folder | no tags | |
| list_labels | no tags | |
| create_label | no tags | |
| update_label | no tags | |
| delete_label | no tags | |
| list_sip_trunks | no tags | |
| get_sip_trunk | no tags | |
| create_sip_trunk | no tags | |
| update_sip_trunk | no tags | |
| delete_sip_trunk | no tags | |
| get_whatsapp_senders | no tags | |
| get_whatsapp_templates | no tags | |
| get_whatsapp_session_status | no tags | |
| send_whatsapp_template | no tags | |
| send_whatsapp_freeform | no tags | |
| generate_ai_reply | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest88b1a8f56ddac2b5
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.1. Pin a release below and the command asks for exactly that one.
0.3.1
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 Famulor 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.