cortex-harness (baka3k/cortex-harness) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 106 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100
9 days ago

cortex-harness

A cognition-aware context and harness orchestration framework that combines Graph DBs, Vector DBs, and LLMs to build structured, memory-consistent, and scalable AI systems.

→ baka3k/cortex-harness· listed on github_code

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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

baka3k

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 →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

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.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 6 credentials: NEO4J_PASS, FALKORDB_PASSWORD, NEO4J_PASSWORD, OPENAI_API_KEY, QDRANT_API_KEY, LLM_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// 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.
configMCP_BACKEND_TIMEOUT
configMCP_FASTMCP_TRANSPORT
configCODE_EMBEDDING_MODEL_PATH
configCODE_EMBEDDING_MODEL
configJINA_MODEL_PATH
configMCP_PRELOAD_EMBEDDER
configQDRANT_COLLECTION
configCODE_GRAPH_PROVIDER
configGRAPH_PROVIDER
configMCP_GRAPH_PROVIDER
configNEO4J_URI
configNEO4J_USER
🔐 secretNEO4J_PASS
configNEO4J_DB
configFALKORDB_GRAPH
configFALKORDB_DATABASE
configMCP_SEARCH_TIMING
configFALKORDB_URI
configFALKORDB_URL
configFALKORDB_PATH
🔐 secretFALKORDB_PASSWORD
configFALKORDB_SSL
configCORTEX_STORAGE_OWNER
configCORTEX_STORAGE_INSTANCE
configEMBED_DEVICE
configFASTMCP_TRANSPORT
configFASTMCP_HOST
configFASTMCP_PORT
configFASTMCP_STREAMABLE_HTTP_PATH
configMCP_SERVER_NAME
configNEO4J_USERNAME
configQDRANT_COLLECTION_DOC
configDEFAULT_ENTITY_TYPES
configENTITY_TYPES_DEFAULT
configUVSet when the executable is not on the default PATH, for example make build UV=/opt/homebrew/bin/uv.
configNO_COLOR
configMCP_UNIFIED_DEFAULT_BACKEND
configWORKFLOW_IMPACT_DISABLED
configEDITOR
configVISUAL
configMCP_ENDPOINT
configCORTEX_DATA_HOME
configQDRANT_CODE_PATH
configEMBED_MODEL
🔐 secretNEO4J_PASSWORD
configMAX_EMBED_CHARS
configEMBED_BATCH_SIZE
configNEO4J_STATE_PATH
configMESSAGE_OUTPUT_DIR
configMESSAGE_QDRANT_COLLECTION
configQDRANT_CACHE_DIR
configPROJECT_ID
configPROJECT_NAME
configPROJECT_LANGUAGE
configPROJECT_REPO
configPROJECT_BUILD_SYSTEM
configGIT_COMMIT_SHA_BEFORE
configGIT_COMMIT_SHA_AFTER
configHF_HOME
configHUGGINGFACE_HUB_CACHE
configTRANSFORMERS_CACHE
configHF_MODULES_CACHE
configCOBOL_LANGUAGE_LIBRARY
configEMBEDDING_MODEL
configEMBED_FALLBACK_TO_CPU
configMCP_QUERY_EMBED_CACHE
configCORTEX_STORAGE_PROJECT_ID
configQDRANT_COLLECTION_CODE
🔐 secretOPENAI_API_KEY
configLLM_SUMMARY_MODEL
configOPENAI_BASE_URL
configLLM_SUMMARY_BATCH
configQDRANT_HNSW_M
configQDRANT_HNSW_EF_CONSTRUCT
configQDRANT_SCALAR_QUANT
🔐 secretQDRANT_API_KEY
configCORTEX_HARNESS_CONFIG_PATH
configMCP_COLLECTION_META_CACHE
configQDRANT_HNSW_EF
configREACT_ROLE_LLM_CLASSIFY
configLLM_API_BASE
🔐 secretLLM_API_KEY
configLLM_MODEL
configLLM_TIMEOUT
configENABLE_WORKFLOW_LLM
configLLM_WORKFLOW_MODEL
configCORTEX_EMBEDDING_FINGERPRINT_CACHE_DIR
configPARSE_RUN_ID
configGIT_COMMIT_SHA
configCORTEX_GRAPH_JOURNAL_MODEGraph-write recovery is controlled by : off,
configFLUTTER_ANALYZER_MODE
configQDRANT_BATCH_SIZE
configQDRANT_TIMEOUT
configQDRANT_RETRIES
configQDRANT_RETRY_SLEEP
configGO_ANALYZER_CACHE_DIR
configCORTEX_DISABLE_GRAPH
// 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

106/106 tools missing one or more hints — list_databases (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); semantic_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_qdrant_collections (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +103 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.

Tool test coverage

34/106 tools referenced in tests (32%)

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

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 3 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 Score](https://m8ven.ai/badge/mcp/baka3k/cortex-harness)](https://m8ven.ai/mcp/baka3k/cortex-harness)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 2ebce13fe2cf5ebc93d0925761407650f04f693e
code hash: 7dc267ee18a53dbfcd21264c2bbc6d8df1e39d2ce78c082ffc03c53df7a9fb36
verified: 9/3/2026, 7:35:51 PM
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