Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AD4M_GQL_URLNoGraphQL endpoint URL for the AD4M executorhttp://localhost:4000/graphql

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
ad4m_agent_statusA

Get the local AD4M agent status: DID, initialization state, keystore lock state.

ad4m_list_perspectivesA

List all Perspectives on the local AD4M executor.

ad4m_create_perspectiveA

Create a new named Perspective. Returns its UUID for subsequent link operations.

ad4m_write_memoryA

Write a signed LinkExpression (source → predicate → target) to a Perspective. Auto-optimizes the graph every 10 writes across all terminals.

ad4m_recallA

Query links from a Perspective by source, predicate, or target. Omit any field to match all.

ad4m_get_neighbourhoodB

Read a shared AD4M Neighbourhood by Perspective UUID.

ad4m_classifyA

Classify a piece of information by which layer it belongs to: ad4m, local, env, or relay. Run this BEFORE ad4m_write_memory if unsure.

ad4m_config_checkA

Check whether mcp-ad4m is registered in the correct config file. Detects the wrong-file misconfiguration that causes silent connection failures.

ad4m_optimizeA

Audit the memory graph for duplicates and stale entries. dry_run: true (default) reports without deleting.

ad4m_statsB

Memory graph statistics: total links, duplicates, breakdown by predicate, oldest and newest entries.

ad4m_delete_memoryA

Remove links from a Perspective by source, predicate, and/or target filter. Returns matched/removed/failed counts.

relay_writeA

Write a cross-terminal relay message to AD4M. Both terminals share the same AD4M executor so state is immediately visible.

relay_readA

Read cross-terminal relay messages from AD4M. Optionally filter by session_id or since a timestamp.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/thefranceway/mcp-ad4m'

If you have feedback or need assistance with the MCP directory API, please join our Discord server