Log inSubmit server
Vector MCP logo

Vector MCP

Manage vector collections and search across an epistemic graph, PostgreSQL/pgvector, Qdrant, or MongoDB Atlas through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Vector MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "vector-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "vector-mcp[mcp]",
        "vector-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

vector-mcp MCP server exposes governed vector collection management and retrieval through two action-routed MCP tools. It uses an epistemic-graph engine by default, with opt-in PostgreSQL/pgvector, Qdrant, and MongoDB Atlas providers. The server supports local stdio connections and networked Streamable HTTP deployments, with runtime filtering for tools and tags. Reach for it when an agent needs controlled vector collection operations and search against one of its supported backends.

Use cases

  • Manage vector collections through an MCP-enabled agent
  • Search an epistemic graph from a compatible AI client
  • Connect agent retrieval workflows to Qdrant
  • Filter exposed tools to reduce model context usage

Key features

  • Collection management over MCP
  • Vector search over MCP
  • Epistemic-graph default backend
  • PostgreSQL/pgvector, Qdrant, and MongoDB Atlas providers
  • Dynamic tool and tag filtering
  • Stdio and Streamable HTTP transports

Tools2

What Vector MCP lets your agent do. Expand a tool for its parameters.

Verified live~808 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

What it can do

From the 2 tools this server returned when we ran it.

Read-only tools · 2
Network at startup2 connections
Files written at startup16

Observed 2026-10-25 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · vector-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars16Stargazers on the source repository.
Last commit4d agoMost recent push to the default branch.
Tools exposed2Callable tools this server registers over MCP.

How Vector MCP works

What vector-mcp does

vector-mcp provides an MCP interface for vector collection management and retrieval. Its default backend is an epistemic-graph engine, while optional provider packages add PostgreSQL/pgvector, Qdrant, or MongoDB Atlas connectivity. The package also includes a vector retrieval ontology, a read-only vector collection inventory preset, and runtime configuration through AgentConfig, environment variables, and secret references.

The exposed MCP surface is intentionally compact: vector_collection_management handles collection-management operations, and vector_search handles search operations. A consolidated vector-mcp-operations workflow is available as the associated skill provider.

How it works

The server uses action-routed tools to keep the MCP surface small and reduce context overhead. Its tool mode can be changed between intent, condensed, verbose, or both; the condensed mode presents the two action-routed tools listed above. Tool toggles can independently enable or disable collection management and search.

Operators can restrict visible tools or toolsets at startup with command-line arguments, environment variables, HTTP SSE headers, or HTTP SSE query parameters. Tool and tag filters can be resolved against known names, descriptions, and tags through a knowledge-graph layer, with a background cache refresh interval of 24 hours.

Setup and configuration

Install the connector-focused package with:

bash
uvx --from 'vector-mcp[mcp]' vector-mcp

Install only the provider extra needed by the deployment, such as vector-mcp[postgres], vector-mcp[qdrant], or vector-mcp[mongodb]. The all extra includes every optional provider along with the agent, Langfuse, and Logfire runtimes. The runtime requires agent-connector-sdk>=0.2.0 and its full epistemic-graph engine contract.

For local IDE use, configure the process over stdio with uvx. For networked deployments, start it with --transport streamable-http and a port, or connect a client to an already deployed MCP URL. Supported deployment forms include stdio, Streamable HTTP, local container or uv, and a remote URL. Secret references such as database credentials and provider API keys can be passed through an alias-aware launcher; other launchers should resolve secrets through their own runtime boundary.

Tools and capabilities

  • vector_collection_management: exposes collection-management operations.
  • vector_search: exposes search operations.
  • Dynamic tool and toolset visibility filtering through CLI options, environment variables, SSE headers, and SSE query parameters.
  • Provider selection for the native epistemic graph, PostgreSQL/pgvector, Qdrant, and MongoDB Atlas.
  • Stdio and Streamable HTTP transports.

Limitations and notes

Provider support is opt-in, and production images are intended to install only the providers they operate. The server does not expose a large fixed set of one-to-one MCP tools by default; its action-routed surface and selected tool mode determine what clients see. Network HTTP deployments require operator-managed host, proxy, and TLS policies; the generated configuration avoids an unauthenticated non-loopback listener. Detailed parameter schemas and validation constraints belong to the usage guide rather than the compact tool listing.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Vector MCP

vector-mcp is an MCP server that connects AI agents to an epistemic-graph vector engine or opt-in PostgreSQL/pgvector, Qdrant, and MongoDB Atlas providers. Its main tools, `vector_collection_management` and `vector_search`, support governed collection operations and vector retrieval through stdio or Streamable HTTP.

Install it with `uvx --from 'vector-mcp[mcp]' vector-mcp`. Add the `postgres`, `qdrant`, or `mongodb` extra when using one of those optional providers, or use the `all` extra for every provider and additional runtimes.

Yes, vector-mcp works with Cursor over stdio. Configure Cursor to launch `uvx --from 'vector-mcp[mcp]' vector-mcp`; it can also connect through a deployed Streamable HTTP endpoint.

Use CLI filters, environment variables, SSE headers, or SSE query parameters to enable or disable tools, toolsets, and tags. The relevant controls include `--tools`, `--toolsets`, `MCP_ENABLED_TOOLS`, `MCP_DISABLED_TOOLS`, and their tag equivalents.

Related MCP servers

All in Databases All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVector MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/vector-mcp?style=directory)](https://allmcps.com/mcp/vector-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/vector-mcp"><img src="https://allmcps.com/api/badge/vector-mcp?style=directory" alt="Vector MCP on AllMCPs" /></a>