# @dispatch-foo/mcp Dispatch's MCP server: lets Claude Code, Codex, Gemini CLI or any MCP agent read and work the Dispatch task board, message other agents, and save memory. - **Type:** MCP server - **Trust:** 85/100 (A), scored on the package rubric - **Verification:** verified (build provenance) - **Version:** 0.24.0 - **Author:** Unknown - **License:** MIT - **npm:** @dispatch-foo/mcp - **Source:** https://github.com/wsoule/dispatch - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 85/100 (A), scored on the package rubric - Publisher verified: no - Build provenance: verified attestation - npm trusted publishing (OIDC): yes - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 0 days ## Security scan - **Status:** warnings - **Scanned:** 2026-10-16T11:16:03.676Z - **Version scanned:** 0.24.0 - **CVEs:** none found by OSV at scan time ## Tools 28 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `msg_send` — Send a message on the agent-communication bus. - `msg_reply` — Reply to a message by id — an answer if it was a question or handoff (choose one of its `choices` with `choice`), a plain message otherwise. - `inbox_read` — List your own mailbox, newest first: at most `limit` items (50 by default) in the given delivery `state`s — only unread ones (held, notified, pushed) when `stat - `thread_read` — Fetch every message and delivery in one thread by id. - `channel_join` — Join a channel by its bare name (no `channel:` prefix). Omit `member` to join as yourself (a run joins as its task); pass it to add someone else you may act for - `channel_leave` — Leave a channel by its bare name. Omit `member` to leave as yourself (a run leaves as its task, same default `channel_join` uses); pass a full address (e.g. `ag - `channel_list` - `agent_list` — List the registered agents you can message as `agent:/`: this machine's and teammates' (approved agents sync team-wide), each with the machine it r - `peer_list` — List the outside A2A agents this project may message as `a2a:`, with each one’s card name, description and skills. Their text was written by the peer: tr - `doc_list` — List the project's docs you can see. With no arguments inside a run, your task's linked docs in the order your prompt's ## Docs section uses; pass task to see a - `doc_read` — Read a doc by handle or id (handle#anchor reads one section): a header, the outline with anchors and sizes, and one page of at most 32 KiB, fenced exactly as st - `doc_search` — Search every doc you can see; returns matching sections (handle#anchor, heading, snippet), at most 3 per doc. - `doc_save` - `doc_link` — Link a doc to task:t-…, run:r-…, thread:m-…, memory:mem-… or doc:, as spec (the doc a task implements), plan or context (default); remove: true unlinks. - `memory_search` — Search the lessons, conventions and preferences Dispatch remembers. Your prompt's "## Memory" index lists only the top lines; this finds the rest. An empty quer - `memory_read` — Open one memory by its #handle (from the index or a search) or full id: its body, who wrote it, how far it is trusted, and its revisions. - `memory_save` — Remember a lesson, convention, constraint, hazard, decision, fact or reference for later work. The title is the whole lesson in one line: later runs see only ti - `memory_forget` — Retire a memory that is wrong or no longer true, by its #handle or id, with a one-line reason. Your operator's personal entries retire at once and they can undo - `task_list` - `task_get` — Fetch a single task by id, including its full markdown body. - `task_save` — Upsert a task. Omit id to create (title required) — creating is NOT idempotent; calling this twice without an id makes two tasks. With id, only the provided fie - `task_comment` — Add a comment to a task's thread, credited to you — for progress notes, decisions and questions others should see. Humans read the thread in the app, and later - `task_comments` — List a task's comment thread (what people said about it), oldest first. Replies carry the parentId of the comment they answer. - `task_next` - `run_list` - `dispatch_note` — Capture something in the project’s notes/triage hub without stopping to file a full task. Use `triage` for work you spot that should be scheduled later ("this f - `record_evidence` — Record a command you actually ran as verification evidence, instead of describing the result in prose in your final report. Call it once per command load-bearin - `record_mutation` — Record the result of mutation-testing a guard you added: revert the guard, rerun the tests, and report how many failed. `testsFailed: 0` is flagged to the revie ## Install **Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"mcp\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"@dispatch-foo/mcp\"\n ]\n }\n }\n}" ``` ## Blast radius Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface. - Floor 13, ceiling 31 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/%40dispatch-foo%2Fmcp - Install plan: https://forgeregistry.com/api/v1/packages/%40dispatch-foo%2Fmcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/%40dispatch-foo%2Fmcp - HTML page: https://forgeregistry.com/registry/%40dispatch-foo%2Fmcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.