Read-only artifact queries for AI assistants: wiring AngusRepo MCP AngusRepo has published documentation for its in-process MCP read-only endpoint, which exposes eight tools prefixed repo_ by default for AI coding agents to query artifact metadata without proxying /maven, /npm, /v2 or other protocol paths. The endpoint requires a portal-issued user access token (PAT) — a Deploy Token (repod_) returns 401 — and is rate-limited to at most 30 successful tools/call per account per minute, with Community edition excluding MCP while Team, Enterprise and Cloud follow the docs. Result projections deliberately drop downloadUrl, checksums, README and full license text, and the server does not download binaries, mint tokens or run cleanup. Read-only artifact queries for AI assistants: wiring AngusRepo MCP A coding agent that asks “which repo holds this coordinate, and what are the dependency and vulnerability counts?” does not need mvn / npm / docker stuffed into the model context. AngusRepo exposes that as an in-process MCP read-only endpoint: the host connects, calls named tools, and the server loo ps back to this process’s management API for metadata projections. Takeaway: Repo MCP is read-only end to end—eight tools prefixed repo by default; it does not proxy /maven, /npm, /v2, or other protocol paths; it does not download binaries, mint tokens, or run cleanup. Community does not include MCP; Team / Enterprise / Cloud follow the docs. Identity must be a portal-issued user access token PAT ; a Deploy Token repod gets 401. How console and clients wire MCP: Connect to AngusRepo via MCP. This article covers how the eight read-only tools split, why PAT and Deploy Token differ, plus rate limits and edition boundaries. Cache consistency: AngusRepo cache architecture. In chat, the same five patterns show up: Locate an ingested artifact and say whether it is quarantined or already scanned. Inspect dependencies, declared licenses, and vulnerability counts. Emit client setup snippets for a repository format password placeholders . Preview what an existing cleanup policy would affect without executing . Read an existing security score snapshot for a repository or tenant. Explicitly out of scope: upload, delete, publish, download, trigger scans, mint tokens. Protocol pulls keep using PAT or Deploy Token—they never enter MCP. IDE / Agent --POST {gateway}/repo/mcp-- Boot /mcp --loopback Bearer-- /api/v1/ GET whitelist An in-process endpoint reuses the permissions and audit already on REST. A separate Node that re-wraps REST would duplicate policy. Loopback has no generic path parameter, so the model cannot invent protocol or download routes. Item Stance Transport Stateless POST; default path /mcp; via gateway {host}/repo/mcp Loopback Base URL is the local Repo port; Bearer forwarded as-is; X-Angus-Client-Source: mcp Registration tools only; no MCP resources / prompts / sampling GM No new GM resources; tool visibility follows existing @PPS codes Instance switches edition config, aligned with user docs : Setting Role angus.mcp.enabled env ANGUS MCP ENABLED, defaults true when unset false skips registering the endpoint; artifact hosting is unaffected angus.mcp.write-enabled Product-fixed false; no write tools Rate limit: at most 30 successful tools/call per account per minute; invalid args return before counting. Community does not seed the System → MCP tab and force-disables /mcp. With a system admin or a role that holds every read permission, tools/list should show exactly eight: Tool Permission notes What it does repo find artifact Artifacts:VIEW Search by name fragment etc.; at least one filter; pageSize clamped to 1–20 repo locate version Artifacts:VIEW Exact primary-file locate; multiple hits → ambiguous + candidates, no guessing repo inspect dependencies Artifact fields Artifacts:VIEW; license findings also need SecurityScans:VIEW Dependencies, declared licenses, vulnerability counts; does not trigger scans repo list repositories Repositories:VIEW Visible repos, no settings repo client setup Repositories:VIEW Same templates as the console; passwords are placeholders repo artifact security Scan history etc. also need SecurityScans:VIEW Quarantine, existing vulnerability counts and scan history; does not trigger scans repo repository score SecurityScans:VIEW Repo/tenant score snapshot—not a single-package score repo cleanup preview CleanupPolicies:VIEW GET preview only; no execution records Result projections deliberately drop downloadUrl, checksums, README, and full license text to shrink model misuse and leak surface. Not in the list: repo search, repo compare versions follow-ups, not registered by default , repo invoke read, repo connection check, or any publish / delete / execute cleanup / mint token. Empty secure or scanTrust=UNKNOWN means not scanned yet, not “safe.” Admission gate is off by default; Repo enforcement vs Security engines matches the product FAQ. Credential Result Portal-issued user access token PAT Can enter MCP; tool set narrows with role repod Deploy Token 401, no tool list OAuth refresh token / other product tokens 401 No Bearer 401 avoid collapsing into in-tool errors that make the model blind-retry Visibility equals that user’s /api/v1 scope—same as the console. MCP does not re-interpret protocol-path repo:read / repo:write. repo:write on a PAT means protocol write—not MCP write. Personal tokens: avatar → Me /profile . CI should use a service account—do not commit a personal login into the repo. Put the token in an env var—never in the repo: { "mcpServers": { "angus-repo": { "url": "https://