Schema | claudecode-infinite-memory

claudecode-infinite-memory

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_MEMORY_WATCH`	No	Enable file watcher for knowledge directory	false
`MCP_MEMORY_DB_PATH`	No	SQLite database path	./memory.sqlite
`MCP_MEMORY_MAX_LIMIT`	No	Maximum search result count	20
`MCP_MEMORY_CHUNK_TOKENS`	No	Knowledge indexing chunk size (approximate tokens)	400
`MCP_MEMORY_DEFAULT_LIMIT`	No	Default search result count	5
`MCP_MEMORY_SESSIONS_PATH`	No	Directory containing session JSONL files	~/.claude/projects
`MCP_MEMORY_SYNC_ON_START`	No	Full sync on server startup	true
`MCP_MEMORY_KNOWLEDGE_PATH`	No	Knowledge directory path; put .md files here for auto-indexing	(empty, disabled)
`MCP_MEMORY_SYNC_COOLDOWN_MS`	No	Cooldown before incremental sync on search (ms)	5000
`MCP_MEMORY_WATCH_DEBOUNCE_MS`	No	File watcher debounce interval (ms)	1500
`MCP_MEMORY_CLAUDE_HISTORY_PATH`	No	Claude Code session history file	~/.claude/history.jsonl
`MCP_MEMORY_CHUNK_OVERLAP_TOKENS`	No	Chunk overlap size (approximate tokens)	80

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lchaoer/claudecode-infinite-memory'

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