NeuronDBBLOCK
NeuronDB PostgreSQL extension: vector similarity search (HNSW, IVFFlat), embeddings, kNN, ML in SQL, and hybrid full-text + vector retrieval.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
PostgreSQL extension for vector similarity search (HNSW, IVFFlat), kNN, embeddings, machine learning, and hybrid full-text + vector search in SQL
[](https://www.postgresql.org/) [](https://github.com/neurondb/neurondb) [](LICENSE) [](https://www.neurondb.ai/docs)
Run the system in 5 minutes
From the repository root:
docker compose -f docker/docker-compose.yml up -d neurondb docker compose -f docker/docker-compose.yml ps # wait until healthy docker compose -f docker/docker-compose.yml exec neurondb psql -U neurondb -d neurondb -c "CREATE EXTENSION IF NOT EXISTS neurondb; SELECT neurondb.version();"
Then run your first vector search: Simple Start or Quick Start.
Table of Contents
Expand full table of contents
- Overview
- Key Capabilities
- Performance Metrics
- Documentation
- Getting Started
- Vector Search & Indexing
- ML Algorithms & Analytics
- ML & Embeddings
- Hybrid Search & Retrieval
- Reranking
- RAG Pipeline
- Background Workers
- GPU Acceleration
- Performance & Security
- Configuration & Operations
- Official Documentation
- [Architecture](#architecture
a6a3f6e6f66cOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add neurondbpy --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env CODACY_API_TOKEN=${CODACY_API_TOKEN} --env DB_PASSWORD=${DB_PASSWORD} --env NEURONAGENT_API_KEY=${NEURONAGENT_API_KEY} -- uvx neurondbpy{
"mcpServers": {
"neurondbpy": {
"command": "uvx",
"args": [
"neurondbpy"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"CODACY_API_TOKEN": "${CODACY_API_TOKEN}",
"DB_PASSWORD": "${DB_PASSWORD}",
"NEURONAGENT_API_KEY": "${NEURONAGENT_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
example-agent | read | A simple example agent |
Trust audit
BLOCKgrade F · trust 52/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (12 observation(s))
- Network
- declared (7 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
if helm package "$CHART_DIR" --sign --key "$sign_key" --keyring ~/.gnupg/secring.gpg 2>&1; then
# ansible_ssh_private_key_file: ~/.ssh/id_rsa
# NEURONDB_CONNECTION_STRING=postgresql://neurondb:neurondb@neurondb-cpu:5432/neurondb
- DATA_SOURCE_NAME=postgresql://neurondb:neurondb@neurondb-cpu:5432/neurondb?sslmode=disable
st=$(curl -s -o /dev/null -w "%{http_code}" --connect-timeout 2 "http://127.0.0.1:8083/health" 2>/dev/null || echo "---")printf "%-26s | %-28s | %s\n" "NeuronDB Cloud Gateway" "http://127.0.0.1:8083" "$st"
st=$(curl -s -o /dev/null -w "%{http_code}" --connect-timeout 2 "http://127.0.0.1:$port/health" 2>/dev/null || echo "---")printf "%-26s | %-28s | %s\n" "$name" "http://127.0.0.1:$port" "$st"
psql "postgresql://neurondb:neurondb@localhost:5433/neurondb" -c "SELECT neurondb.version();"
psql "postgresql://neurondb:neurondb@localhost:5433/neurondb" <<EOF
postgresql://neurondb:neurondb@localhost:5433/neurondb
.clang-format
.pre-commit-config.yaml
.helmignore
text_hash = hashlib.md5(text.encode()).hexdigest()
text_hash = hashlib.md5(query_text.encode()).hexdigest()
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../python'))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../python'))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../python'))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../python'))
os.path.join(os.path.dirname(__file__), '../../ann-benchmarks'),
numpy, psycopg2-binary, beir, tqdm
numpy, psycopg2-binary, mteb, beir, ragas, transformers, datasets, sentence-transformers
numpy, psycopg2-binary, h5py, tqdm
requests, psycopg2-binary, numpy, h5py, datasets, numpy, h5py
Gates applied: no_behavioural_pass.
a6a3f6e6f66cfull audit observations/trust-audit/mcp-server/neurondb__neurondb-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a6a3f6e6f66c | BLOCK | F | 52 | first audit |
Questions
What is the NeuronDB MCP server?
NeuronDB PostgreSQL extension: vector similarity search (HNSW, IVFFlat), embeddings, kNN, ML in SQL, and hybrid full-text + vector retrieval.
What tools does NeuronDB expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is NeuronDB safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (52/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does NeuronDB need?
It reads ANTHROPIC_API_KEY, CODACY_API_TOKEN, DB_PASSWORD, NEURONAGENT_API_KEY, OPENAI_API_KEY and PGPASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (a6a3f6e6f66c), read on 2026-10-08. The repository is watched and re-audited when it changes.