Enables AI assistants to search and query documentation with flexible backend configurations (ChromaDB, Xenova embeddings) and supports multiple chunking strategies via an MCP server.
Caution. Specific findings reduced this grade. They are listed on the page. 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
bsreeram08
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Elysia affected by arbitrary code injection through cookie config
Elysia has a string URL format ReDoS
Prototype Pollution in sheetJS
AGENT_ENABLEDAGENT_NAMEAGENT_OPTIONSAPI_BASE_URLCHROMA_URLOld variables like STORAGE_PROVIDER, EMBEDDING_PROVIDER, , XENOVA_MODEL are supported for backward-compat in parsing, but are deprecated.CHUNKING_NAMEConfigure via =langchain and CHUNKING_OPTIONS={"strategy":"recursive","chunkSize":3000,"chunkOverlap":150}.CHUNKING_OPTIONSConfigure via CHUNKING_NAME=langchain and ={"strategy":"recursive","chunkSize":3000,"chunkOverlap":150}.CHUNKING_PROVIDERCHUNK_OVERLAPnumber Back-compat: overlap between chunks (default: 150)CHUNK_SIZEnumber Back-compat: target chunk size (default: 3000)EMBEDDINGS_NAME=transformersjsEMBEDDINGS_OPTIONS{"model":"Xenova/all-MiniLM-L6-v2","maxBatchSize":50}EMBEDDING_PROVIDEROld variables like STORAGE_PROVIDER, , CHROMA_URL, XENOVA_MODEL are supported for backward-compat in parsing, but are deprecated.HTTP_PORTbun run upload-server:prod # Default :3001 (set ). Use :dev for watch modeLOG_ENABLEDLOG_LEVELMAX_BATCH_SIZEDeprecated (still parsed for backward compatibility): STORAGE_PROVIDER, EMBEDDING_PROVIDER, CHROMA_URL, XENOVA_MODEL, , UPLOAD_SERVER_PORT, UPLOAD_SERVER_HOST.MAX_CHUNK_SIZEnumber Back-compat: hard cap for chunk size (default: 5000)STORAGE_NAMEstring Storage provider name (e.g., chroma)STORAGE_OPTIONS{"url":"http://localhost:8000"}STORAGE_PROVIDEROld variables like , EMBEDDING_PROVIDER, CHROMA_URL, XENOVA_MODEL are supported for backward-compat in parsing, but are deprecated.XENOVA_MODELOld variables like STORAGE_PROVIDER, EMBEDDING_PROVIDER, CHROMA_URL, are supported for backward-compat in parsing, but are deprecated.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
4/4 tools missing one or more hints — list_documentation_sets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_documentation (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_documentation_set (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.
Tool inputs are validated
3/4 tool handlers declare input schemas (75%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
3/4 tool handlers wrap calls in try/catch (75%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 6 high severity in production deps — @modelcontextprotocol/sdk@1.2.0 (high), @modelcontextprotocol/sdk@1.2.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/22 production deps stale: @xenova/transformers@2024-05-29 (2y)
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/bsreeram08-cogni-docs-1fbug5)?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