Schema | Codex Native Memory

Codex Native Memory

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CODEX_NATIVE_MEMORY_HOME`	No	Override the default data directory (default: %USERPROFILE%\.codex-native-memory on Windows, ~/.codex-native-memory on Unix).

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
memory_searchC	Search imported Codex conversations, summaries, observations, and memories.
memory_recentC	List recent imported Codex sessions.
memory_contextC	Build project-oriented memory context: summaries, decisions, open questions, observations, recent sessions, and optional query matches.
memory_bootstrapC	Import recent memory, summarize pending sessions, and return a dynamic project profile plus project-oriented context.
memory_importC	Import changed Codex transcript JSONL files into memory.
memory_rememberC	Store a pinned memory item for future Codex project bootstrap/context.
memory_notesB	List pinned memory items for a project/cwd, including global user memory.
memory_updateC	Update a pinned memory item by id.
memory_exportC	Export pinned memory and a computed project profile as a JSON bundle.
memory_import_bundleC	Import pinned memory items from a memory_export JSON bundle. Provide payload or payload_json.
memory_forgetB	Delete a pinned memory item by id.
memory_sourcesC	List attached AI sources and external review targets.
memory_healthA	Show Codex Native Memory database health and counts.

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/BulbuLbul86/codex-native-memory'

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