F
Warning
30/100
11 days ago

cortexmd

Long-term memory + code-navigation brain for AI agents, over the Model Context Protocol (MCP).

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

Code Verified⚡ Live Monitored: not connected

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

Leicas

Source: github_code

Is this your MCP?

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

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 5 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
⚠️
Tests do not pass
Either the test suite is broken or the code regressed. Either way the published behaviour can’t be verified by the publisher’s own tests.
🔐
You'll be asked for 6 credentials: ANTHROPIC_API_KEY, API_KEY, BRAIN_TOKEN, DASHBOARD_PASSWORD, MCP_API_KEY, RERANKER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies1 critical5 high2 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highglob@11.0.2GHSA-5j98-mcp5-4vw2

glob CLI: Command injection via -c/--cmd executes matches with shell:true

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEY
🔐 secretAPI_KEYBRAIN_VAULT=/data/brain SOURCE_VAULTS=/data/sources/ =... \
configAPI_PORT
configAPP_VERSION
configAUTO_LINK
configAUTO_LINK_MIN_CONFIDENCE
configAUTO_LINK_RELATED
configAUTO_LINK_RELATED_MAX
configAUTO_LINK_RELATED_MIN_SCORE
configAUTO_SEED_KG
configBITEMPORAL_KG
configBRAIN_SERVER
🔐 secretBRAIN_TOKEN
configBRAIN_VAULT~/.local/share/cortexmd/brain \
configCLAUDE_CONFIG_DIR
configCODE_AUTO_PROJECT_ON_RECALL
configCODE_NAV_LANGS
configCODE_REPOS
configCORS_ORIGINS
configCO_RECALL
configCO_RECALL_WEIGHT
🔐 secretDASHBOARD_PASSWORD
configDATA_DIRno Where SQLite cache + HNSW index live.
configDREAM_CRON
configDREAM_SCHEDULE
configEMBEDDINGS_DATA_DIR
configEMBEDDING_MODELno Embedding model id.
configENABLE_EMBEDDINGSno Toggle semantic search (HNSW + transformers). false = lexical-only fast path.
configENABLE_KG
configENABLE_RERANKERno Optional LLM reranker; provider/host fully optional, no default hardware/model.
configEVAL_ARMS
configEVAL_BITEMPORAL
configEVAL_COMPARE
configEVAL_DATASET
configEVAL_EMBEDDINGS
configEVAL_GRAPH
configEVAL_K
configEVAL_OUT
configEVAL_REAL_VAULT
configEVAL_REPORT_JSON
configEVAL_SMOKE
configGIT_SHA
configIDENTITY_FILE
configIDLE_DREAM
configIDLE_DREAM_BUDGET_MS
configIDLE_DREAM_CHECK_MS
configIDLE_DREAM_MS
configINDEX_REBUILD_INTERVAL_MSno Lexical index rebuild cadence (default 60000).
configLOG_LEVELno info (default), debug, etc.
configMACHINE_ID
configMAX_NOTE_SIZE
configMAX_REQUEST_SIZE
configMAX_REQUEST_SIZE_BYTES
🔐 secretMCP_API_KEY
configMCP_URL
configMEMORY_CONTRADICTION_DETECT
configMEMORY_VALIDITY
configMETRICS_FLUSH_INTERVAL_MS
configOBSIDIAN_HOOK_MINIMAL
configOBSIDIAN_MEMORY_DISABLE
configOBSIDIAN_NO_HINTS
configOBSIDIAN_TOOL_PROFILE
configPPR_RECALL
configPPR_SYNONYMY_THRESHOLD
configPROXY_AUTH
configPROXY_AUTH_USER
configPUBLIC_URLHTTP only External base URL for OAuth callbacks. No hardcoded default.
configRECALL_CENTRALITY_WEIGHT
🔐 secretRERANKER_API_KEY
configRERANKER_BASE_URL
configRERANKER_MODEL
configRERANKER_PROVIDER
configRERANKER_TIMEOUT_MS
configSESSION_RETENTION_MS
configSESSION_TIMEOUT_MS
configSOURCE_REFRESH_INTERVAL_MS
configSOURCE_VAULTS/path/to/vault \
configVAULT_RO_HAPLY
configVAULT_RO_PERSO
configVAULT_RW
configXDG_DATA_HOME
// quality suggestions

Tool 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

85/85 tools missing one or more hints — agent_diary_append (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agent_diary_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agents_get (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +82 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 2/85 tools referenced in tests (2%)

Write tests that reference each tool by name so every tool has at least one test.

Tests pass

npm test failed — tests do not pass

Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.

Shell command execution

41 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

2 secret values sent to console.log

Redact or omit secret values from log output.

Production dependencies are patched

0 critical, 5 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

4/26 production deps abandoned (no release in 2+ years): tree-sitter-dart@2023-02-24 (3.5y), gray-matter@2023-07-12 (3.1y), hnswlib-node@2024-03-11 (2.4y)

Domain consistency

npm scope @cortexmd doesn't match GitHub owner leicas

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 10 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/leicas-cortexmd-rzyuq9?variant=verified)](https://m8ven.ai/mcp/leicas-cortexmd-rzyuq9)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 37359e56080dac49bd1d2442b0365997122ecf4a
code hash: 9f7598d044b1a5bc4078c9b9c2222a9ca06e15be85a00e0e5e5e33d79a6abd4c
verified: 8/8/2026, 7:52:48 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client