MCP Security Index
Before you install an MCP server, see what it can do. AxioRank enumerates the tools each server declares (read-only, it never calls one) and grades the blast radius of what it can do: write, delete, execute, credential, and wildcard-scope capabilities. Scan a server not listed here.
Scan a server that is not listed
Scans a remote MCP server or agent card by URL. For a local stdio server, run npx @axiorank/mcpaudit.
32 servers in Data
- –Supabase SupabaseData · scan pending
- –PostgreSQL Anthropic (MCP reference, archived)Data · scan pending
- –Memory (Knowledge Graph) Anthropic (MCP reference)Data · scan pending
- –Hugging Face Hugging FaceData · scan pending
- –MongoDB MongoDBData · scan pending
- –Neon NeonData · scan pending
- –Redis RedisData · scan pending
- –Qdrant QdrantData · scan pending
- –Elasticsearch ElasticData · scan pending
- –Pinecone Developer PineconeData · scan pending
- –Chroma ChromaData · scan pending
- –ClickHouse ClickHouseData · scan pending
- –Amazon DynamoDB AWS LabsData · scan pending
- –Snowflake Snowflake LabsData · scan pending
- –Neo4j Cypher Neo4j LabsData · scan pending
- –Prisma Postgres PrismaData · scan pending
- –MotherDuck and DuckDB MotherDuckData · scan pending
- –Amazon Redshift AWS LabsData · scan pending
- –Amazon Aurora PostgreSQL AWS LabsData · scan pending
- –MySQL (benborla) Ben BorlaData · scan pending
- –Google BigQuery ergutData · scan pending
- –SQLite Model Context ProtocolData · scan pending
- –TiDB PingCAPData · scan pending
- –Microsoft Clarity MicrosoftData · scan pending
- –Cloudflare GraphQL Analytics CloudflareData · scan pending
- –Couchbase CouchbaseData · scan pending
- –AutoRFP.ai AutoRFPData · scan pending
- –Kubit Kubit-AIData · scan pending
- –matih-mcp matih-labsData · scan pending
- –mcp-analytics embeddedlayersData · scan pending
- –rolli-mcp rolliincData · scan pending
- –omni-datastream autonomous-computerData · scan pending
How the grades work
A grade measures blast radius: how much a server could do if it were compromised or misinstructed, based on the capabilities it declares (write, delete, execute, credential access, wildcard scope). It is not a vulnerability assessment and not a judgment of the vendor. Lower is better: A is 0 to 19, up to F at 80 and above. The scan is read-only. It lists tools and never calls one.
Run a server? You can scan it yourself and embed your grade. See something off? Every server page links a re-scan.
Govern the MCP servers your agents use
AxioRank is the security gateway for AI agents: allowlist servers, block risky tool calls, and get an audit trail of every action.
Start free