KnowledgeMCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
KnowledgeMCP
A team-scoped RAG knowledge base on AWS, served as an MCP server and a REST API. Upload PDFs, Markdown or text files to S3. Ask questions from Claude Desktop, Claude Code or any app, and get answers with citations (document + page/section). Each user only sees answers from the documents their team may read. If the answer isn't in those documents, it says so instead of guessing.

What it does
Ingestion | S3 upload → Lambda parses PDF/Markdown/text → section-aware chunks (page or heading kept) → Amazon Titan Text Embeddings V2 → Aurora PostgreSQL + pgvector. Re-uploads of unchanged files are skipped; deletes remove the document. |
Hybrid search | Vector search (pgvector HNSW, cosine) + keyword search (Postgres full-text), merged with Reciprocal Rank Fusion, then re-ranked by Amazon Rerank 1.0 (falls back to a local re-ranker if the call fails). |
Answers with citations | Claude on Bedrock answers only from the retrieved passages, citing |
Access control | The first S3 folder is the team ( |
Guardrails | Input validation and prompt-injection checks on questions; retrieved text is sanitized and wrapped as untrusted data; relevance gate and |
MCP server | Tools |
Evaluation | 35-case test set: recall@k, MRR, answer correctness, citation accuracy, refusal accuracy, access control, injection blocking, optional LLM-judge faithfulness, p50/p95 latency, cost per query. |
Observability | Structured JSON logs, CloudWatch metrics via Embedded Metric Format, X-Ray traces, per-step timings in every answer, and a CloudWatch dashboard. |
Infrastructure | AWS CDK (Python): Aurora Serverless v2 (scales to 0), S3, three container Lambdas, HTTP API with throttling, Secrets Manager, dashboard, optional $10/month budget alert. |
Related MCP server: senza-knowledge-mcp
Architecture

Asking a question: API key → user and teams → input guardrail → embed question → vector + keyword search (both filtered to the user's teams) → RRF fusion → re-rank → relevance gate → sanitize sources → Claude → citation check → answer, or a refusal.
Design decisions
Aurora Serverless v2 with min 0 ACU instead of an always-on RDS instance. The database pauses when idle, so a portfolio project doesn't pay for compute 24/7. Trade-off: the first request after a pause waits while it resumes (about 15 s); the Data API client retries automatically.
RDS Data API instead of Lambda-in-VPC. Lambdas reach the database over HTTPS with IAM, so there is no NAT gateway or VPC endpoint to pay for, and no connection pooling to manage.
One container image, three handlers (API, ingest, migrate), selected with the Lambda
cmd.Schema migrations run after every deploy through a CDK Trigger (idempotent
IF NOT EXISTS).Same SQL locally and on AWS:
PsycopgExecutor(local Postgres) andDataApiExecutor(Aurora) share one store, so integration tests run against a real pgvector database.Honest naming: the keyword side uses Postgres full-text ranking (
ts_rank_cd), which is similar in spirit to BM25 but is not BM25.
Results
Measured against the deployed stack (Bedrock models) with python -m evals.run_evals --target http --judge bedrock.
Metric | Value |
Retrieval recall@5 | to be measured after deployment |
Answer correctness | to be measured |
Citation accuracy | to be measured |
Faithfulness (LLM judge) | to be measured |
Refusal accuracy (unanswerable + other-team) | to be measured |
Access control / injection blocking | to be measured |
Latency p50 / p95 (warm) | to be measured |
Model cost per question | to be measured |
CI also runs the evals with offline stand-in models on every push. Those numbers only test the plumbing, but CI fails if access control or injection blocking drops below 100%.
Run it locally (no AWS needed)
docker compose up --build # Postgres + pgvector and the API; sample docs are indexed on start
open http://localhost:8000/docs # interactive API docsOr without Docker, against any Postgres that has pgvector:
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev,local]"
export DATABASE_URL=postgresql://postgres:postgres@localhost:5432/kmcp
python -m knowledgemcp.cli ingest sample_docs
python -m knowledgemcp.cli ask "How many vacation days can I carry over?" --teams hr
pytest -q # 50 tests (includes the pgvector integration test)Local mode uses offline stand-ins (word-hash embeddings, an extractive "LLM", lexical re-ranker) so everything
runs without credentials. Set EMBEDDER=bedrock LLM=bedrock RERANKER=bedrock to use the real models.
Deploy to AWS
Prerequisites: AWS CLI configured (aws sts get-caller-identity works), Docker running, Node.js 18+, Python 3.12.
In the Bedrock console (us-west-2), make sure your account can use Titan Text Embeddings V2,
Amazon Rerank 1.0 and Claude Haiku 4.5.
pip install -e ".[dev,local]" -r infra/requirements.txt
npm install -g aws-cdk
cd infra
cdk bootstrap # once per account/region
cdk deploy -c alert_email=you@example.com # prints ApiUrl, BucketName, ApiKeysSecretArn, ...Then load documents, create a key and ask:
aws s3 sync ../sample_docs s3://<BucketName>/ # team = first folder
python ../scripts/create_api_key.py --user teja --teams hr,engineering,finance --secret-id <ApiKeysSecretArn>
curl -s <ApiUrl>/ask -H "x-api-key: kmcp_..." -H "content-type: application/json" \
-d '{"question": "Who approves expenses above 1,000 US dollars?"}'Tear everything down with cdk destroy.
Use it from Claude Desktop (MCP)
pip install -e ".[mcp]"Add this to claude_desktop_config.json:
{
"mcpServers": {
"knowledgemcp": {
"command": "/absolute/path/to/.venv/bin/knowledgemcp-mcp",
"env": { "KMCP_API_URL": "https://<id>.execute-api.us-west-2.amazonaws.com", "KMCP_API_KEY": "kmcp_..." }
}
}
}For development without AWS, use "env": {"KMCP_LOCAL": "1", "KMCP_TEAMS": "hr,engineering", "DATABASE_URL": "..."}.
Evaluate
# one key per persona: hr, engineering, finance, none (public only)
python scripts/create_api_key.py --user eval-hr --teams hr --secret-id <ApiKeysSecretArn> # repeat per persona
# evals/keys.json -> {"hr": "kmcp_...", "engineering": "kmcp_...", "finance": "kmcp_...", "none": "kmcp_..."}
python -m evals.run_evals --target http --url <ApiUrl> --keys evals/keys.json --judge bedrockResults are written to evals/results/ as JSON and Markdown.
Project structure
src/knowledgemcp/
loaders.py, chunking.py PDF/Markdown/text → sections → chunks (page/section kept)
embeddings.py Titan V2 embedder (+ offline hash embedder)
db.py, store.py Data API / psycopg executors; pgvector store with team filtering
search.py, rerank.py hybrid retrieval, RRF, Bedrock re-ranker (+ lexical fallback)
guardrails.py, llm.py input/source/output guardrails; Claude via Bedrock Converse
rag.py the question-answering pipeline, metrics and cost
api.py, auth.py FastAPI app + Lambda handler; hashed API keys
mcp_server.py MCP tools and resources
ingest.py, handlers_ingest.py, cli.py
infra/ AWS CDK app (Python) + synth tests
evals/ test set and evaluation harness
tests/ pytest suite (moto, botocore Stubber, real pgvector)
sample_docs/ fictional company documents (hr, engineering, finance, public)Limitations
Prompt-injection detection is pattern-based. It is one layer of several (system prompt, data wrapping, SQL team filtering, citation checks), not a complete defense.
HNSW search with a team filter can return fewer than
kresults when a team owns a small share of chunks; at larger scale, use pgvector iterative scans or per-team partitions.The sample documents describe a fictional company.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Search and manage your team's knowledge from MCP clients.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to ask plain-language questions and receive answers grounded only in documents the configured role is cleared to read, with the same access-controlled tools available across any client.MIT
- AlicenseAqualityCmaintenanceEnables coding agents to query a team knowledge base via MCP, performing semantic search and asking questions that return grounded, citation-backed answers from ingested documents.4MIT
- FlicenseNot gradedqualityBmaintenanceEnables retrieval-augmented question answering with source-grounded citations, document retrieval, and idempotent ingestion through MCP tools.-

neonrecallofficial
AlicenseBqualityBmaintenanceEnables MCP clients to search ingested documents and ask citation-backed questions through the search_docs and ask tools.2MIT