Muninn
Provides persistent memory for AI coding agents via MCP, allowing them to recall fragility, decisions, and bugs across sessions.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
ravnltd
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
recallYour memory. One tool for all context. Give it files (pre-edit warnings), a query (search memory), or a task (planning context). Returns fragility, co-changers, decisions, learnings, issues, blast radius — everything you need in one call.
rememberRecord a decision or learning. Natural language — auto-categorizes as decision or learning based on content. Use for novel insights only; routine file knowledge is captured automatically.
trackTrack issues. Actions: add (record bug/debt), resolve (mark fixed).
muninnRun a muninn command. Available: status, reindex, db, fragile, outcome, list, show, search.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Drizzle ORM has SQL injection via improperly escaped SQL identifiers
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono vulnerable to arbitrary file access via serveStatic vulnerability
Hono: Path traversal in toSSG() allows writing files outside the output directory
DB_PATHMUNINN_API_TOKENMUNINN_AUTH_TOKENMUNINN_HOMEMUNINN_HTTP_PORTMUNINN_LOG_LEVELMUNINN_MODEMUNINN_OUTPUT_FORMATMUNINN_PRIMARY_URLMUNINN_REDIS_URLMUNINN_SYNC_INTERVALTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
4/4 tools missing one or more hints — recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); remember (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); track (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
No eval / new Function
1 eval() or new Function() call — dynamic code execution
Replace eval / Function with explicit parsing or safer alternatives.
Shell command execution
7 calls in production code run through a shell (src/commands/git.ts:37, src/commands/git.ts:51, src/commands/git.ts:71)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Production dependencies are patched
0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.25.3 (high), drizzle-orm@0.45.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/ravnltd/muninn)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check