C
Limited view
67/100
19 days ago

Confluent Support RAG MCP Server

An MCP server that provides hybrid search over Confluent support articles and lets AI assistants save solved problems back into the knowledge base.

Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

Limited view: static analysis for Python is partially covered.

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

BhwinGT

Source: Glama

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
6 tools verified — handlers match their declared behaviour
2 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 3 credentials: AZURE_CLIENT_SECRET, MCP_JWT_SIGNING_KEY, OLLAMA_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.
configEMBED_MODELqwen3-embedding:0.6b Dense embeddings. Always local.
configQDRANT_HOST/ QDRANT_PORT localhost / 6333 (docker) host → qdrant
configQDRANT_PORTQDRANT_HOST / localhost / 6333 (docker) host → qdrant
configQDRANT_COLLECTIONconfluent_support
configMCP_HOST/ MCP_PORT 127.0.0.1 / 8000 (docker) → 0.0.0.0, which lets other containers reach it
configMCP_PORTMCP_HOST / 127.0.0.1 / 8000 (docker) → 0.0.0.0, which lets other containers reach it
configMCP_AUTH_ENABLEDCompany-only sign-in =true + all the AZURE_... vars + PUBLIC_MCP_URL + ALLOWED_EMAIL_DOMAINS
configAZURE_CLIENT_IDIdentifies this app. Public. Tokens are checked to have been issued for this ID, so one meant for another app can't be replayed.
🔐 secretAZURE_CLIENT_SECRETThe app's password, proving to Microsoft that requests claiming to be this app really are. Keep secret.
configAZURE_TENANT_IDWhich Entra directory may issue tokens. The outer gate: outsiders are rejected by Microsoft before reaching your server.
configAZURE_API_SCOPEaccess Must match the scope you exposed in Entra
configAZURE_TOKEN_ISSUER(blank) Only if the app still issues v1.0 tokens
configPUBLIC_MCP_URLCompany-only sign-in MCP_AUTH_ENABLED=true + all the AZURE_... vars + + ALLOWED_EMAIL_DOMAINS
configALLOWED_EMAIL_DOMAINSCompany-only sign-in MCP_AUTH_ENABLED=true + all the AZURE_... vars + PUBLIC_MCP_URL +
configALLOWED_EMAILSset? → address must be on that exact list
🔐 secretMCP_JWT_SIGNING_KEYNot about Microsoft. Signs the server's own session tokens. Leave it blank and a random one is generated at every startup, logging everyone out on each restart.
configFASTEMBED_CACHE_DIR./model_cache (docker) → the mounted volume
configOLLAMA_HOST
configTOP_K_RESULTS5 Default results per search
configRERANK_MIN_SCORE│ → sort by score → drop below → keep top_k
configCHUNK_SIZE300 Target words per chunk
configSUPPORT_BASE_URLScrape fails naming a URL with no protocol is blank in .env. A blank value overrides the script's fallback rather than deferring to it.
configSUPPORT_CATEGORY_IDS360004404872,360005831891,360005822052
configSUPPORT_COOKIETo build the knowledge base . The other two scrape values ship pre-filled, see Step 3
configINFERENCE_MODELgemma4:31b orchestrator.py chat only.
🔐 secretOLLAMA_API_KEYCloud inference in orchestrator.py
// quality suggestions

Tool annotations

3/6 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

3/6 tools missing one or more hints — confluent_search_documents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); confluent_search_official_articles (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); confluent_search_saved_conversations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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 inputs are validated

5/6 tool handlers declare input schemas (83%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

3/6 tool handlers wrap calls in try/catch (50%)

Wrap each tool handler body in try/catch and return a structured error response.

License file

No license file

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

Tests exist

No test files found

Add tests that exercise each declared tool.

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 6 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/bhwingt-mcp-server-conluent-rag-n6sn93)](https://m8ven.ai/mcp/bhwingt-mcp-server-conluent-rag-n6sn93)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: e33037fa8931c30b9efdef6a3ed884fe6cda71bb
code hash: 8c561b803428183c7b3d7ed8cae08d391d455478358ba2719a75ebb40a71d74e
verified: 8/2/2026, 9:05:39 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