Schema | tdai-memory-mcp

tdai-memory-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`TDAI_DB_PATH`	No	The SQLite database file path	~/.local/share/tdai-memory-mcp/memory.db
`TDAI_STORAGE`	No	Storage backend: sqlite, pgvector, file, or tdai-gateway	sqlite
`TDAI_PIPELINE`	No	Pipeline stage: noop, atom, scenario, or mermaid	noop
`TDAI_AUDIT_LOG`	No	Writes the audit log to audit.jsonl	true
`TDAI_LLM_MODEL`	No	The LLM model name	gpt-4o-mini
`TDAI_LLM_API_KEY`	No	The LLM API key for pipeline features
`TDAI_LLM_BASE_URL`	No	The LLM endpoint	https://api.openai.com/v1
`TDAI_REDACT_SECRETS`	No	Redacts API keys and tokens on capture	true
`TDAI_MAX_TOKENS_RECALL`	No	The token cap per recall response	4000
`TDAI_MAX_TOKENS_SEARCH`	No	The token cap per search response	8000

Features and capabilities supported by this server

Capability	Details
`tools`	{}
`resources`	{}

Functions exposed to the LLM to take actions

Name	Description
recallA	Retrieve relevant past memory. Call this tool before you answer the user. Use it when the user references past work or when the task needs project context.
captureA	Save a decision, a learning, or a task outcome to memory. Call this tool after you complete a non-trivial task, make a decision, or fix a bug with a known root cause.
searchA	Search memory by keyword or by semantic similarity. Use this tool when recall is too broad and you need specific facts.
forgetA	Delete specific memory entries. Use this tool only when the user requests a deletion. Do not auto-forget.
handoffA	Write a structured handoff packet for the next agent session. Call this tool at the end of a session, or before you switch to a different agent. The next agent calls recall to load this packet and continue without re-reading files. This saves 60-85% of tokens compared to re-discovering context.
adrA	Record an Architecture Decision Record (ADR). Use this tool when you make a technical decision that future agents should know about. The ADR is stored as a structured capture and can be recalled by any agent working on the same project.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
`Recent captures`	The 20 most recent memory captures.
`Memory statistics`	Summary statistics for the memory database.

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tinhien11/tdai-memory-mcp'

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