Google Search Console integration for Model Context Protocol (MCP)
Facebook 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.
What it does
Facebook Pages MCP server for the Meta Graph API — publishing, insights, moderation, messaging
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ivanbbaev-facebook-mcp '--' npx -y @ivanbaev/facebook-mcp
Facebook costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Facebook 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.
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 ivanbbaev-facebook-mcp '--' npx -y @ivanbaev/facebook-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take FB_SYSTEM_TOKEN (System-user access token (Business Manager). Takes precedence over FB_ACCESS_TOKEN and FB_PAGE_TOKEN when several are set.), FB_ACCESS_TOKEN (Primary user access token. At least one of FB_SYSTEM_TOKEN, FB_ACCESS_TOKEN or FB_PAGE_TOKEN must be set.), FB_PAGE_TOKEN (Long-lived Page access token used as a fallback credential when no user or system-user token is configured.), FB_APP_ID (Meta app ID; combined with FB_APP_SECRET it forms the app access token used to authorize /debug_token inspection.), FB_APP_SECRET (Meta app secret. When set, appsecret_proof is attached to every call so a stolen bare token cannot be used on its own.), FB_PAGE_ID (Default Facebook Page ID, used when a tool call omits an explicit profile argument.), FB_API_VERSION (Graph API version to target. Defaults to the tested pinned version; other values are accepted verbatim as an escape hatch but are not tested.), FB_REQUEST_TIMEOUT_MS (Per-request timeout in milliseconds; integer in [1, 600000].), FB_HOST_CONCURRENCY (Maximum number of in-flight requests per Graph host; integer in [1, 64].), FB_MAX_RESULT_CHARS (Character budget applied by the result shaper before a tool result is truncated; integer in [500, 10000000].), FB_WRITE_MODE (Write gating mode: plan (validating dry-run preview, the default) or apply. It never covers the irreversible and spend tiers, which always need a per-call apply), FB_CONFIRM_TOKEN (Operator confirmation token for out-of-band approval of irreversible or spend actions. The server prompts through MCP elicitation where the client supports it;), FB_MEDIA_DIR (Directory permitted for local media uploads. Unset means URL-only uploads and no local file access at all.), FB_JOURNAL_PATH (Path to the append-only write journal. Defaults to the XDG/%APPDATA% state path; the file is created owner-only (0600) and rotates by size.), FB_TOOL_PACKAGES (Comma-separated tool packages or profiles to expose (e.g. core,posts,reader, or the profiles core|all|reader|publisher|moderator|ads). Omit for the default prof), FB_PACKAGES_DENY (Comma-separated packages to exclude even when FB_TOOL_PACKAGES enables them. Deny wins over allow.), FB_PACKAGES_READONLY (Comma-separated packages whose write tools are not registered at all; the read tools of those packages stay available.), FB_TRANSPORT (Transport protocol: stdio (default) or http. The http transport binds 127.0.0.1 only and fails closed without FB_HTTP_TOKEN.), FB_HTTP_TOKEN (Bearer token guarding the HTTP transport; required when FB_TRANSPORT=http (the server refuses to start without it).), FB_HTTP_PORT (Port for the HTTP transport (loopback only); used when FB_TRANSPORT=http. Integer in [1, 65535].), FB_AD_ACCOUNT_ID (Default ad account ID (act_… or the bare numeric id) for the opt-in ads package.), FB_ADS_BUDGET_CEILING (Hard ceiling for any ads budget write, in minor currency units (e.g. cents). Non-negative integer; a write above it is refused.), FB_LOG_LEVEL (Stderr log verbosity: debug, info, warn or error. Logs never go to stdout — that is the stdio protocol channel.) if you want to set them.
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.
This listing has not published its tool surface here yet, so what a client will ask you to approve is whatever the manifest declares at install time.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
This listing has not published its tool list here yet. Nothing is shown here rather than another listing’s tools, which is what this page used to do.
- 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 Facebook or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
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
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 0.7.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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.
Any signed-in account that does not publish Facebook can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.