Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Bulkpublish 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
10
downloads a day
local
runs on your machine
510
downloads in 30d
What it does
Model Context Protocol server for BulkPublish — lets AI assistants manage social media posts, channels, media, and analytics.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'BULKPUBLISH_API_KEY=${BULKPUBLISH_API_KEY}' --transport stdio bulkpublish-mcp '--' npx -y @bulkpublish/mcp-server
# 2 — ask your agent for something these tools do
# list_channels, list_platforms, create_post and 70 more
It needs BULKPUBLISH_API_KEY: this reads it from your environment, so export it first.
Bulkpublish costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BUAll 1 server
@bulkpublish1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Bulkpublish as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads BULKPUBLISH_API_KEY (Your BulkPublish API key (starts with bp_)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx BULKPUBLISH_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'BULKPUBLISH_API_KEY=${BULKPUBLISH_API_KEY}' --transport stdio bulkpublish-mcp '--' npx -y @bulkpublish/mcp-serverReconnect, 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 asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: BULKPUBLISH_API_KEY — Your BulkPublish API key (starts with bp_). You set it in your own client’s config, on your machine — this marketplace never holds it.
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
73 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.
List all connected social media channels (X/Twitter, Instagram, LinkedIn, Facebook, TikTok, etc.). Returns channel ID, platform, account name, and token status.
No parameter schema on file.
List every social platform BulkPublish supports and whether it is currently available.
No parameter schema on file.
Create a new social media post. Can be saved as a draft or scheduled for a specific time. Supports platform-specific content overrides, media attachments, labels, and thread format.
No parameter schema on file.
List posts with optional filters for status, search text, date range, channel, and label. Returns paginated results with platform statuses and metrics, ordered newest-first by publishedAt if the post is live, else scheduledAt, else createdAt.
No parameter schema on file.
Get a single post by ID with full details including platform statuses, labels, media files, recurring schedule info, and metrics.
No parameter schema on file.
Publish a draft or scheduled post immediately. The post will be queued for publishing to all its target channels.
No parameter schema on file.
Retry publishing a failed or partially failed post. Only retries the platforms that failed, not the ones that already succeeded.
No parameter schema on file.
Approve a post awaiting team approval. Requires a role with post:approve (owner, admin, approver).
No parameter schema on file.
Reject a post awaiting team approval. Requires a role with post:approve.
No parameter schema on file.
Upload a media file (image or video) from a URL or local file path. The file is stored in BulkPublish for use in posts. Supported formats: JPEG, PNG, WebP, GIF, MP4, MOV, WebM. Max 100MB. Provide either url OR filePath, not both.
No parameter schema on file.
List uploaded media files with optional search and pagination. Returns file metadata including URLs, dimensions, and labels.
No parameter schema on file.
Get an analytics summary for a date range. Returns total posts, status breakdown (published, failed, scheduled), per-platform stats, and daily post counts.
No parameter schema on file.
List all labels available for tagging posts and media.
No parameter schema on file.
Create a new label for organizing posts or media files.
No parameter schema on file.
Check current account usage. Returns daily/monthly post counts, scheduled post counts, channel counts, and media storage usage.
No parameter schema on file.
Update an existing post. Can change content, schedule, media, labels, status, and platform-specific settings.
No parameter schema on file.
Delete a post by ID. Only draft and failed posts can be deleted.
No parameter schema on file.
Get engagement metrics for a published post. Returns likes, comments, shares, impressions, and other platform-specific metrics. IMPORTANT: every platform entry carries
No parameter schema on file.
Publish a post as a story on Facebook or Instagram.
No parameter schema on file.
Perform a bulk action on multiple posts. Supports deleting, retrying, or rescheduling multiple posts at once.
No parameter schema on file.
Get the organization
No parameter schema on file.
Check the health status of a connected channel. Returns token validity, connection status, and any issues.
No parameter schema on file.
Get platform-specific options for a channel (e.g. available post types, character limits, media requirements).
No parameter schema on file.
Search for @mention suggestions on a channel. Useful for finding users/pages to mention in posts.
No parameter schema on file.
Get details of a single media file by ID. Returns metadata, URL, dimensions, and labels.
No parameter schema on file.
Delete a media file by ID. Removes the file from storage and detaches it from any posts.
No parameter schema on file.
Update an existing label
No parameter schema on file.
Delete a label by ID. Removes the label from all associated posts or media.
No parameter schema on file.
List all recurring post schedules. Returns schedule name, cron expression, target channels, and active status.
No parameter schema on file.
Create a new recurring post schedule. Posts are automatically created and published on the chosen frequency.
No parameter schema on file.
Update an existing recurring schedule. Can change name, content template, frequency/timing, timezone, media, or active status. The next run time is recomputed by the server when timing changes.
No parameter schema on file.
Delete a recurring schedule by ID. Stops all future posts from this schedule.
No parameter schema on file.
List saved channel sets — named channel groupings for one-click multi-channel targeting. Returns id, name, and channelIds for each set, ordered by name.
No parameter schema on file.
Create a channel set — a saved channel grouping for one-click multi-channel targeting. Names are unique per organization (a duplicate fails with a 409, code DUPLICATE_NAME); an organization can have up to 50 sets.
No parameter schema on file.
Update a channel set
No parameter schema on file.
Delete a channel set by ID. Does not affect the channels themselves.
No parameter schema on file.
List RSS autopost feeds — RSS/Atom feeds polled every 15 minutes whose new items automatically become posts. Returns name, feedUrl, channelIds, mode, fieldMapping (how items are rendered into posts; null = default), enabled, lastCheckedAt, and lastError for each feed.
No parameter schema on file.
Add an RSS autopost feed. The feed is polled every 15 minutes and new items become posts on the chosen channels. The server validates that feedUrl is a reachable public RSS 2.0 or Atom feed. An organization can have up to 20 feeds.
No parameter schema on file.
Update an RSS autopost feed (partial update). Note: changing feedUrl re-baselines the feed — its check state resets and only items published after the change are posted, so the new feed
No parameter schema on file.
Delete an RSS autopost feed by ID. Stops polling; already-created posts are kept.
No parameter schema on file.
Start a chunked (multipart) direct-to-storage upload for large media — videos up to 1GB, images up to 100MB. Returns r2Key, uploadId, the fixed partSize (10485760 bytes = 10MB), and one presigned PUT URL per part (valid 3600s). PUT each 10MB slice to its URL, collect each response
No parameter schema on file.
Complete a chunked upload: the server assembles the uploaded parts, verifies the stored object (existence, size, magic bytes, storage quota) and records the media file — same verification and response shape as finalize_media_upload. A failed assembly automatically aborts the upload.
No parameter schema on file.
Abort an in-progress chunked upload and free its stored parts.
No parameter schema on file.
Reserve a presigned R2 upload URL for a direct browser upload (used by the composer UI). For scripted uploads use upload_media instead.
No parameter schema on file.
Record an uploaded R2 object as a media file after the browser PUT (pairs with create_media_upload; used by the composer UI).
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 Bulkpublish 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 1.42.0 · 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 · 2 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestd6170ecb619702588c485aa43a65c8e621fa657388d611be94f82972a7a71c9e
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 (73 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>".
1 of the 73 recovered tools are registered only when !HIDE_BILLING_TOOLS holds (dist/index.js:1576) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 72.
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.
72 tools are registered unconditionally · 1 more only when !HIDE_BILLING_TOOLS holds (dist/index.js:1576) — typically when a key or option is configured. All 73 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_channels | no tags | |
| list_platforms | no tags | |
| create_post | no tags | |
| list_posts | no tags | |
| get_post | no tags | |
| publish_post | no tags | |
| retry_post | no tags | |
| approve_post | no tags | |
| reject_post | no tags | |
| upload_media | untrusted-inputexternal-sink | untrusted-input: handler fetches a URL taken from its input (fetch(mediaUrl) at dist/index.js:1247; external-sink: handler sends an HTTP POST (fetch(uploadUrl) at dist/index.js:1282 |
| list_media | no tags | |
| get_analytics | no tags | |
| list_labels | no tags | |
| create_label | no tags | |
| list_hashtag_groups | no tags | |
| create_hashtag_group | no tags | |
| update_hashtag_group | no tags | |
| delete_hashtag_group | no tags | |
| list_templates | no tags | |
| create_template | no tags | |
| update_template | no tags | |
| delete_template | no tags | |
| list_calendar_notes | no tags | |
| create_calendar_note | no tags | |
| update_calendar_note | no tags | |
| delete_calendar_note | no tags | |
| share_post | no tags | |
| unshare_post | no tags | |
| list_review_links | no tags | |
| create_review_link | no tags | |
| delete_review_link | no tags | |
| list_client_connect_links | no tags | |
| create_client_connect_link | no tags | |
| delete_client_connect_link | no tags | |
| update_media | no tags | |
| get_quota_usage conditional | no tags | |
| update_post | no tags | |
| delete_post | no tags | |
| get_post_metrics | no tags | |
| publish_story | no tags | |
| bulk_posts | no tags | |
| get_queue_slot | no tags | |
| get_channel_health | no tags | |
| get_channel_options | no tags | |
| search_mentions | no tags | |
| get_media | no tags | |
| delete_media | no tags | |
| update_label | no tags | |
| delete_label | no tags | |
| list_schedules | no tags | |
| create_schedule | no tags | |
| update_schedule | no tags | |
| delete_schedule | no tags | |
| list_channel_sets | no tags | |
| create_channel_set | no tags | |
| update_channel_set | no tags | |
| delete_channel_set | no tags | |
| list_rss_feeds | untrusted-input | untrusted-input: keyword "rss" |
| create_rss_feed | untrusted-input | untrusted-input: keyword "rss" |
| update_rss_feed | untrusted-input | untrusted-input: keyword "rss" |
| delete_rss_feed | untrusted-input | untrusted-input: keyword "rss" |
| create_multipart_upload | no tags | |
| complete_multipart_upload | no tags | |
| abort_multipart_upload | no tags | |
| create_media_upload | no tags | |
| finalize_media_upload | no tags | |
| list_conversations | no tags | |
| get_conversation | no tags | |
| reply_to_conversation | no tags | |
| update_conversation | no tags | |
| list_post_comments | no tags | |
| reply_to_comment | no tags | |
| moderate_comment | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestd6170ecb61970258
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 1.42.0. Pin a release below and the command asks for exactly that one.
1.42.0
5 Oct 2026
latestNo release note was published with this version.
1.33.2
11 Sep 2026
No release note was published with this version.
1.18.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Bulkpublish 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.