Skip to main content

PostgreSQL MCP

Project description

Apache AGE MCP Server

These tools provide an interface for AI Agents to manage multiple graphs in Apache AGE. They expose tools for creating, updating, administering, and visualizing graphs.

Tool Name Description Parameters
get_or_create_graph Get or create a graph with the specified name. graph_name: str
list_graphs List all graph names in the database.
upsert_graph Upsert both vertices and edges into the specified graph (deep merge). graph_name: str, vertices: List[Dict[str, Any]], edges: List[Dict[str, Any]]
upsert_edge Insert or update an edge's properties in a graph non-destructively. graph_name: str, label: str, edge_start_ident: str, edge_end_ident: str, properties: Dict[str, Any]
upsert_vertex Insert or update a vertex's properties in a graph non-destructively. graph_name: str, vertex_ident: str, label: str, properties: Dict[str, Any]
drop_graphs Drop one or more graphs by name. graph_names: List[str]
drop_vertex Remove a vertex by ident. graph_name: str, vertex_ident: str
drop_edge Remove an edge by ident. graph_name: str, edge_ident: str
generate_visualization Generate a single-page HTML file visualizing a graph using vis.js and pyvis. graph_name: str

Server Installation

Install the latest release using pipx (recommended for CLI/server tools):

# Install
pipx install agemcp

# Postgres DSN / MCP Server Defaults
agemcp config

# Start the server
agemcp run

You should see something like this:

INFO:     Starting MCP server 'agemcp' with transport 'streamable-http' on http://0.0.0.0:8000/mcp/
INFO:     Started server process [13951]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

Client Installation

VSCode

  1. Open Command Palette (Cmd+Shift+P or Ctrl+Shift+P).
  2. Select MCP: Add Server...
  3. Choose "HTTP" option.
  4. Enter the server URL (e.g., http://localhost:8000/mcp/).
  5. Enter a "server id" (e.g., agemcp).
  6. Select Global for the scope.
  7. Done. (It should appear in the extensions sidebar.)

Roo / Cline / Claude

{
  "mcpServers": {
    "agemcp": {
      "url": "http://localhost:8000/mcp/",
      "type": "streamable-http",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agemcp-0.5.2.tar.gz (61.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agemcp-0.5.2-py3-none-any.whl (54.3 kB view details)

Uploaded Python 3

File details

Details for the file agemcp-0.5.2.tar.gz.

File metadata

  • Download URL: agemcp-0.5.2.tar.gz
  • Upload date:
  • Size: 61.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for agemcp-0.5.2.tar.gz
Algorithm Hash digest
SHA256 30cde0671b19c164e5fce2fecba372f2e115c6fcca6542186052eb140bad6f8d
MD5 24af8d911e5ce1b9ecf5a1014defc07e
BLAKE2b-256 d77c3abcda52c65bcc33e0a11de2a4e15d85f2918fccf86b0a9643827084cdd6

See more details on using hashes here.

File details

Details for the file agemcp-0.5.2-py3-none-any.whl.

File metadata

  • Download URL: agemcp-0.5.2-py3-none-any.whl
  • Upload date:
  • Size: 54.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for agemcp-0.5.2-py3-none-any.whl
Algorithm Hash digest
SHA256 e59ba1d29d2cd30f1d5b2dcaa344d265c3d50f313a55ed4e000199e76c203d35
MD5 e44f940ed7d828a82e4c71d7526fa564
BLAKE2b-256 d30fefff7549ceecd7ea855746cf4c10e8b0a296f5ed8b3547d39b8a45536542

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page