F
Warning
0/100
6 days ago

knowledge-base-mcp-server

Provides tools for listing and retrieving content from different knowledge bases using semantic search capabilities.

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

jeanibarz

Source: modelscope

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
🚨
Hardcoded credentials detected
3 live-looking API keys in source: 1 GitHub PAT (classic), 1 AWS access key, 1 Google API key
⚠️
Known vulnerabilities in dependencies: 16 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 4 credentials: HUGGINGFACE_API_KEY, KB_OPENROUTER_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies16 high4 medium10 low

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

high@langchain/core@0.3.62GHSA-r399-636x-v7f6

LangChain serialization injection vulnerability enables secret extraction

high@modelcontextprotocol/sdk@1.17.2GHSA-345p-7cg4-v4c7

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

high@modelcontextprotocol/sdk@1.17.2GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.17.2GHSA-w48q-cv73-mx4w

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

highaxios@1.6.7GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

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.
configASK_KNOWLEDGE_DESCRIPTION"Answer from engineering runbooks with citations."
configBENCH_BATCH_CONCURRENCIES
configBENCH_BUILD_ROOT
configBENCH_CLI_SEARCH_REPETITIONS
configBENCH_FAISS_INDEX_PATH
configBENCH_FIXTURE_CHUNKS_PER_FILE
configBENCH_FIXTURE_CHUNK_CHARS
configBENCH_FIXTURE_FILES
configBENCH_INCLUDE_BATCH_QUERY
configBENCH_INCLUDE_CLI_SEARCH
configBENCH_INCLUDE_INDEX_STORAGE
configBENCH_KNOWLEDGE_BASES_ROOT_DIR
configBENCH_MODEL_ID
configBENCH_MODEL_NAME
configBENCH_PROVIDER
configBENCH_PUSHDOWN_K
configBENCH_PUSHDOWN_NTOTAL
configBENCH_PUSHDOWN_REPETITIONS
configBENCH_PUSHDOWN_SELECTIVITY
configBENCH_QUERIES
configBENCH_RESULTS_DIR
configBENCH_RESULTS_PREFIX
configBENCH_STUB_EMBED_MS_PER_INPUT
configBENCH_WORKSPACE_ROOT
configEMBEDDING_PROVIDERSet =ollama to use local Ollama embeddings
configEXTRACTION_TEXT_CACHE_DIR
configFAISS_INDEX_PATHThe wrapper prints the active KNOWLEDGE_BASES_ROOT_DIR, ,
configFRONTMATTER_EXTRAS_WIRE_VISIBLE
configHF_HOME
🔐 secretHUGGINGFACE_API_KEYyour_api_key_here
configHUGGINGFACE_ENDPOINT_URLto the full POST URL; explicit endpoint URLs
configHUGGINGFACE_MODEL_NAMEBAAI/bge-small-en-v1.5
configHUGGINGFACE_PROVIDERhf-inference # Optional, router provider for serverless inference
configINDEXING_BATCH_SIZE
configINGEST_EXCLUDE_PATHS"drafts/,scratch.md"
configINGEST_EXTRA_EXTENSIONS".json,.yaml"
configKB_ACTIVE_MODEL
configKB_AGE_BUDGET_HOURS
configKB_AGE_BUDGET_HOURS_ALPHA
configKB_AGE_BUDGET_HOURS_BETA
configKB_ASK_REDACT_OUTBOUND
configKB_BUILD_COMMIT
configKB_CHUNK_OVERLAPparam-int==0:128:32 \
configKB_CHUNK_SIZEparam-int==256:1024:128 \
configKB_CONTEXTUAL_RETRIEVAL
configKB_DAEMON_URL
configKB_DENSE_DEGRADE_ON_PROVIDER_ERROR
configKB_FLAT_SEARCH_P95_ADVISORY_MS
configKB_FS_CONCURRENCY
configKB_FS_WATCH
configKB_GATE_LLM_ENDPOINT
configKB_GATE_LLM_MODEL
configKB_GATE_LLM_TIMEOUT_MS
configKB_HNSW_EF_CONSTRUCTION
configKB_HNSW_EF_SEARCH
configKB_HNSW_M
configKB_HNSW_RANDOM_SEED
configKB_INDEXING_BENCH_BATCHES
configKB_INDEXING_BENCH_BATCH_SIZE
configKB_INDEXING_BENCH_EMBED_MS
configKB_INDEXING_BENCH_INSERT_MS
configKB_INDEXING_CONCURRENCY
configKB_INDEX_TYPE
configKB_INDEX_VERSION_RETENTION
configKB_INGEST_ENABLED
configKB_INGEST_SECRET_SCAN
configKB_INJECTION_GUARD_WRAP_CLOSE
configKB_INJECTION_GUARD_WRAP_OPEN
configKB_LARGE_FILE_POLICY
configKB_LLM_CONFIG_DIR
configKB_LLM_ENDPOINT
configKB_LLM_FAKE
configKB_LLM_MODEL
configKB_LLM_PROVIDER
configKB_LLM_STATE_DIR
configKB_LOG_FORMATor LOG_FILE. See [docs/mcp-logging.md](docs/mcp-logging.md)
configKB_LOG_VERBOSE
configKB_MAX_EXTRACTED_TEXT_BYTES
configKB_MAX_FILE_BYTES
configKB_MAX_FILTER_ITEMS
configKB_MAX_GLOB_CHARS
configKB_MAX_GLOB_WILDCARDS
configKB_MAX_QUERY_CHARS
configKB_MIN_FREE_DISK_BYTES
configKB_MUTATION_AUDIT_LOG
🔐 secretKB_OPENROUTER_API_KEY
configKB_REFRESH_QUIESCE_MS
configKB_RELEVANCE_GATE
configKB_RERANKEnable the cross-encoder reranking stage. off
configKB_RERANK_MODELCross-encoder model id used for reranking. (built-in default)
configKB_RERANK_TOP_NHow many top candidates to feed into the reranker. (built-in default)
configKB_RUN_E2E
configKB_SECRET_SCAN_BYPASS_KBS
configKB_SLOW_QUERY_MS
configKB_STATS_DESCRIPTION"Report engineering KB index and transport health."
configKNOWLEDGE_BASES_ROOT_DIR$HOME/knowledge_bases
configKOOKR_BIN
configLAZY_IMPORTS_TRACE_FILE
configLIST_KNOWLEDGE_BASES_DESCRIPTION"List available engineering knowledge bases."
configLIST_MODELS_DESCRIPTION"List embedding models registered for engineering retrieval."
configLOG_FILELogging can be routed to a file by setting =/path/to/logs/knowledge-base.log. Log verbosity defaults to info and can be adjusted with LOG_LEVEL=debuginfowarnerror.
configMCP_BIND_ADDRexport =127.0.0.1 # default — loopback only
configMCP_PORTexport =8765 # default
configMCP_TRANSPORTexport =http # stdio (default), sse, or http
configOLLAMA_BASE_URL
configOLLAMA_MODELdengcao/Qwen3-Embedding-0.6B:Q8_0 # Default embedding model
configOLLAMA_NUM_PARALLEL
🔐 secretOPENAI_API_KEY"message": " environment variable is required when using OpenAI provider"
configOPENAI_MODEL_NAMEtext-embedding-3-small
🔐 secretOPENROUTER_API_KEY
configREINDEX_TRIGGER_PATH
configREINDEX_TRIGGER_POLL_MS
configRETRIEVE_KNOWLEDGE_DESCRIPTION"Search engineering runbooks, RFCs, and postmortems."
configTRANSFORMERS_CACHE
configRAGQA_REFRESH_FIRST
// quality suggestions

Tool annotations

3/11 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

11/11 tools missing one or more hints — list_knowledge_bases (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); retrieve_knowledge (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ask_knowledge (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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

Only 0/2 tool handlers declare input schemas (0%)

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

No hardcoded API keys

3 live-looking API keys in source: 1 GitHub PAT (classic), 1 AWS access key, 1 Google API key

Move secrets to environment variables (process.env.X) or your secret manager.

Shell command execution

5 child_process/subprocess calls in production code — runs shell commands (benchmarks/utils.ts:27, src/build-info.ts:43, src/cli-bug-report.ts:286)

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

Production dependencies are patched

0 critical, 16 high severity in production deps — @langchain/core@0.3.62 (high), @modelcontextprotocol/sdk@1.17.2 (high)

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

Dependency freshness

4/21 production deps abandoned (no release in 2+ years): proper-lockfile@2022-06-24 (4.1y), faiss-node@2023-10-15 (2.8y), pickleparser@2023-10-15 (2.8y)

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 Verified](https://m8ven.ai/badge/mcp/jeanibarz-knowledge-base-mcp-server-nbtbpm?variant=verified)](https://m8ven.ai/mcp/jeanibarz-knowledge-base-mcp-server-nbtbpm)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 12ef4b60b9a4015c1521510fc8bfe7859a840c9c
code hash: 08a2c71d32f25f0c56561dbccf46ba1b66a5a22ebab3d1856c2c93044c55e42f
verified: 8/13/2026, 9:53:34 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