Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
Action-routed MCP and agent interfaces for governed vector collection management and retrieval. The native default is epistemic-graph. Secure opt-in providers cover PostgreSQL/pgvector, Qdrant, and MongoDB Atlas.
vector_collection_management and Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
vector_searchvector-mcp-operations workflowUse the smallest extra set required by the deployment:
uvx --from 'vector-mcp[mcp]' vector-mcp
The runtime requires agent-connector-sdk>=0.2.0 and its self-contained full
epistemic-graph engine contract. A bare numeric-only or partial engine profile is not a
supported deployment.
For a selected storage provider:
uv add 'vector-mcp[postgres]'
uv add 'vector-mcp[qdrant]'
uv add 'vector-mcp[mongodb]'
The all extra enables every supported optional provider plus the agent, Langfuse, and
Logfire runtimes. Production images should install only the providers they operate.
The package includes a neutral agent-start configuration containing only the command, condensed tool mode, and tool toggles. Runtime values are inherited from AgentConfig or injected by the operator. Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.
This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.
Auto-generated from the live MCP server — do not edit by hand.
MCP_TOOL_MODE=condensed)2 action-routed tool(s) · 0 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (intent default — the six verb-tools, granular set loaded on demand · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.
Detailed tool schemas, parameter shapes, and validation constraints are preserved in the usage guide.
This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.
The operator can configure tool filtering via multiple input channels:
--tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLSMCP_ENABLED_TAGS / MCP_DISABLED_TAGSx-mcp-enabled-tools / x-mcp-disabled-toolsx-mcp-enabled-tags / x-mcp-disabled-tags?tools=tool1,tool2?tags=tag1When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.
Install the connector-focused
[mcp]extra. Examples usevector-mcp[mcp]to add FastMCP / FastAPI throughagent-connector-sdk[mcp].
{
"mcpServers": {
"vector-mcp": {
"command": "uvx",
"args": [
"--from",
"vector-mcp[mcp]",
"vector-mcp"
],
"env": {
"MCP_TOOL_MODE": "intent",
"COLLECTION_MANAGEMENTTOOL": "True",
"DATABASE_TYPE": "epistemic_graph",
"DB_PASSWORD_REF": "secret://runtime/db-password",
"DB_PORT": "5432",
"DB_USERNAME_REF": "secret://runtime/db-username",
"MONGODB_MAX_POOL_SIZE": "20",
"MONGODB_REQUEST_TIMEOUT_MS": "30000",
"MONGODB_URI_REF": "secret://runtime/mongodb-uri",
"POSTGRES_MAX_POOL_SIZE": "20",
"POSTGRES_REQUEST_TIMEOUT": "30",
"QDRANT_API_KEY_REF": "secret://runtime/qdrant-api-key",
"QDRANT_REQUEST_TIMEOUT": "30",
"SEARCHTOOL": "True",
"VECTOR_DB_TYPE": "epistemic_graph"
}
}
}
}
Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.
{
"mcpServers": {
"vector-mcp": {
"command": "uvx",
"args": [
"--from",
"vector-mcp[mcp]",
"vector-mcp",
"--transport",
"streamable-http",
"--port",
"8000"
],
"env": {
"TRANSPORT": "streamable-http",
"HOST": "127.0.0.1",
"PORT": "8000",
"MCP_TOOL_MODE": "intent",
"COLLECTION_MANAGEMENTTOOL": "True",
"DATABASE_TYPE": "epistemic_graph",
"DB_PASSWORD_REF": "secret://runtime/db-password",
"DB_PORT": "5432",
"DB_USERNAME_REF": "secret://runtime/db-username",
"MONGODB_MAX_POOL_SIZE": "20",
"MONGODB_REQUEST_TIMEOUT_MS": "30000",
"MONGODB_URI_REF": "secret://runtime/mongodb-uri",
"POSTGRES_MAX_POOL_SIZE": "20",
"POSTGRES_REQUEST_TIMEOUT": "30",
"QDRANT_API_KEY_REF": "secret://runtime/qdrant-api-key",
"QDRANT_REQUEST_TIMEOUT": "30",
"SEARCHTOOL": "True",
"VECTOR_DB_TYPE": "epistemic_graph"
}
}
}
}
Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:
{
"mcpServers": {
"vector-mcp": {
"url": "http://localhost:8000/vector-mcp/mcp"
}
}
}
Run a reviewed container image as a least-privilege stdio child (no listener or published port):
docker run -i --rm \
--read-only \
--cap-drop=ALL \
--security-opt=no-new-privileges \
--pids-limit=256 \
--tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
-e TRANSPORT=stdio \
-e MCP_TOOL_MODE=intent \
-e COLLECTION_MANAGEMENTTOOL=True \
-e DATABASE_TYPE=epistemic_graph \
-e DB_PASSWORD_REF \
-e DB_PORT=5432 \
-e DB_USERNAME_REF \
-e MONGODB_MAX_POOL_SIZE=20 \
-e MONGODB_REQUEST_TIMEOUT_MS=30000 \
-e MONGODB_URI_REF \
-e POSTGRES_MAX_POOL_SIZE=20 \
-e POSTGRES_REQUEST_TIMEOUT=30 \
-e QDRANT_API_KEY_REF \
-e QDRANT_REQUEST_TIMEOUT=30 \
-e SEARCHTOOL=True \
-e VECTOR_DB_TYPE=epistemic_graph \
registry.example.invalid/vector-mcp@sha256:<digest> vector-mcp
For containerized network HTTP, supply an authenticated TLS ingress (or
direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy
CIDR policy through the operator-owned deployment profile. The generator
does not emit an unauthenticated non-loopback listener.
Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.
vector-mcp can also run as a local container (Docker / Podman / uv) or be
consumed from a remote deployment. The
Deployment guide has full, copy-paste
mcp_config.json for all four transports — stdio, streamable-http,
local container / uv, and remote URL:
mcp_config.json via uvx,
docker run, or podman run, or point at a local streamable-http container by url.https://vector-mcp.example.invalid/mcp using the "url" key.25 package + 20 inherited variable(s). Auto-generated from .env.example + the shared agent-utilities set — do not edit.
Every variable the server reads, grouped by purpose. See .env.example for the
canonical, copy-paste list — including the DATABASE_TYPE / GRAPH_SERVICE_SOCKET /
GRAPH_SERVICE_AUTH_SECRET connection settings for the native epistemic-graph backend. Backend
endpoints, database locations, and credentials for opt-in providers (Postgres/Qdrant/Mongo/
Chroma/Couchbase) are never README-documented literal values or MCP tool arguments — they resolve
through AgentConfig and secret:///env:///vault:// references at runtime.
Each action-routed tool can be disabled individually via its toggle env var (set to false).
The full list is in the Available MCP Tools table above.
See .env.example for a copy-paste starting point.
The package contributes its skills, prompts, ontology, and source connector through Python entry points. The collection-inventory connector is intentionally read-only and registers collection metadata, not document or embedding payloads.
Generated connector signatures must be recreated only after the installed MCP schema is observed and a release signing key is provided at runtime. A signature from an older tool schema or ontology must never be copied forward.
Low-cost checks that do not start providers:
python -m compileall -q vector_mcp
Provider tests use mocked SDK boundaries and make no network calls. Live qualification is a separate deployment gate and must use operator-provided AgentConfig and secrets.
The slim :mcp streamable-http container (docker/mcp.compose.yml) publishes
0.0.0.0:8000 with a /health check; see Deployment for the full
compose service definition.
See LICENSE.
agent-utilities-deploymentProvision this package with the consolidated agent-utilities-deployment
workflow. It selects an installed-package, editable-source, or immutable-container
path; records only runtime secret and TLS-profile references in AgentConfig; and
runs doctor, registration, policy, observability, and rollback gates. Ask your agent
to "deploy vector-mcp with agent-utilities-deployment".
The repository embeds no deployment profile, credential value, certificate path, or
environment-specific endpoint. Supply those at runtime through AgentConfig and the
configured secret provider.
Pick the extra that matches what the operator want to run:
# MCP server only (recommended for tool hosting — slim deps)
uv pip install "vector-mcp[mcp]"
# Full agent runtime (Pydantic AI + epistemic-graph engine)
uv pip install "vector-mcp[mcp]"
# Everything (development)
uv pip install "vector-mcp[all]" # or: python -m pip install "vector-mcp[all]"
The shared connector pipeline renders a slim :mcp image (vector-mcp[mcp], entrypoint
vector-mcp) from pyproject.toml at release time:
pipelines-connector render --root .
docker build -t knucklessg1/vector-mcp:mcp docker/
The render command creates the release-owned docker/mcp.compose.yml; it runs the image with
the configured host publication.
epistemic-graph)Graph storage, vector search and queries are served by epistemic-graph, run as its own database container. Deployment recipes (single-node + Raft HA), connection config, and the database architecture are in the epistemic-graph deployment guide.
Contributions are welcome! Please ensure code quality by running local checks before submitting pull requests:
ruff format .ruff check .mypy .pytestVector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Vector läuft lokal über stdio.
Zuletzt geprüft: 2026-11-14. Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
