# cuemap-mcp Local memory and context retrieval for AI agents through CueMap. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.7.4 - **Author:** io.github.cuemap-dev - **License:** Unknown - **npm:** cuemap-mcp - **Source:** https://github.com/cuemap-dev/cuemap-mcp - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 14 days ## Security scan - **Status:** clean - **Scanned:** 2026-09-21T17:00:52.951Z - **Version scanned:** 0.7.4 - **CVEs:** none found by OSV at scan time ## Tools 31 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `cuemap_init_preview` — Preview supported repository files without ingesting content. Call this before first-time repository initialization, present the grouped paths to the user, and - `cuemap_init` — Apply a user-confirmed repository ingestion scope and start CueMap's incremental filesystem watcher. Always call cuemap_init_preview first for a new repository - `cuemap_add` — Store a natural-language memory in CueMap. Uses the repository-scoped default project unless one is supplied, creates it when needed, and applies deterministic - `cuemap_intent_classify` — Classify text with CueMap's local intent model and return recall/memory eligibility signals. Scores are ranking signals, not calibrated probabilities. - `cuemap_status` — Check CueMap background ingestion progress for a project. After cuemap_init, poll this tool until verified_complete is true. An initial idle status with 0/0 wri - `cuemap_projects` — List CueMap projects, summary metadata, and whether each project is currently loaded in RAM. - `cuemap_project_save` — Persist the current state of a CueMap project without unloading it. Package operations save automatically; use this only when an explicit durable checkpoint is - `cuemap_project_load` — Load a persisted CueMap project into RAM before a latency-sensitive operation. Normal project requests load automatically, so use this for explicit warm-up. - `cuemap_project_unload` — Persist and unload a CueMap project from RAM to reduce memory use. Use only when the user explicitly asks to unload or free inactive project memory; active proj - `cuemap_project_pack` — Write a ready-to-query .cuemap package for one project to a local file. The package contains sensitive project content; use only after the user explicitly appro - `cuemap_project_package_load` — Install and warm a local .cuemap package. Use only after the user explicitly approves the exact package path; existing projects are never overwritten. - `cuemap_project_push` — Pack and upload a CueMap project with the engine host's configured AWS CLI. Use only after explicit approval of the exact S3 destination; an existing object at - `cuemap_project_pull` — Download, install, and warm a .cuemap package with the engine host's configured AWS CLI. Use only after explicit approval of the exact S3 source; existing proje - `cuemap_project_sync` — Fast-forward a project through immutable history at an S3 sync root. Pushes local-only changes, pulls remote-only changes, and refuses divergent histories or st - `cuemap_stats` — Read CueMap statistics for the repository-scoped project or globally across the engine. - `cuemap_memory_get` — Get one stored memory as readable text with source metadata. Pass the memory_id and owning project_id from recall as memory_id and project. Does not expand neig - `cuemap_memory_reinforce` — Reinforce one CueMap memory, optionally along specific cue pathways. - `cuemap_memory_delete` — Permanently delete one CueMap memory. Set confirmed=true only after explicit user confirmation. - `cuemap_ingest_url` — Explicitly ingest content from a URL, optionally crawling same-domain links. Use only when the user asks to ingest that URL. - `cuemap_ingest_content` — Explicitly ingest supplied raw content into CueMap. Use only when the user asks to persist that content. - `cuemap_ingest_file` — Explicitly ingest one local file into CueMap. Use only for a file the user has placed in scope and asked to ingest. - `cuemap_project_export` — Export a cursor-paginated page of memories from a CueMap project. - `cuemap_project_artifacts` — Inspect CueBridge artifact metadata for a CueMap project without reloading or mutating it. - `cuemap_alias_list` — List manual cue aliases associated with one cue. - `cuemap_alias_add` — Add a manual weighted mapping from one cue to another. - `cuemap_alias_merge` — Merge multiple cues into one canonical cue. Set confirmed=true only after explicit user confirmation. - `cuemap_lexicon_inspect` — Inspect one cue and its Lexicon relationships. - `cuemap_lexicon_graph` — Read the current Lexicon graph for a project. - `cuemap_lexicon_wire` — Manually wire a token to a canonical Lexicon cue. - `cuemap_lexicon_delete` — Permanently delete one Lexicon entry. Set confirmed=true only after explicit user confirmation. - `cuemap_recall` — Recall evidence for a focused question; follow up with narrower queries as needed. Returns engine JSON with project_id and memory_id handles, source metadata, a ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"cuemap\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"cuemap-mcp\"\n ]\n }\n }\n}" ``` ## Blast radius Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on your machine. - Floor 37, ceiling 61 (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/cuemap-mcp - Install plan: https://forgeregistry.com/api/v1/packages/cuemap-mcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/cuemap-mcp - HTML page: https://forgeregistry.com/registry/cuemap-mcp - 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.