Schema | ainative-opencode-memory-mcp

ainative-opencode-memory-mcp

Official

Describes the environment variables required to run the server.

Name	Required	Description	Default
`AINATIVE_API_KEY`	Yes	Required. Free at ainative.studio
`AINATIVE_API_URL`	No	Override for self-host	https://api.ainative.studio
`OPENCODE_MEMORY_NAMESPACE`	No	Isolate memories per project	opencode

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
opencode_store_memoryA	Store a fact, decision, convention, or code snippet so your OpenCode agent remembers it in future sessions. Use for things like architecture decisions, naming conventions, gotchas, or user preferences.
opencode_search_memoryA	Semantic search over everything the agent has remembered. Returns the most relevant memories for a query.
opencode_recall_contextA	Pull the most relevant remembered context for the current coding task — call this at the START of a session to reload what the agent knew.
opencode_memory_statsA	Report how many memories are stored for this OpenCode namespace.
opencode_clear_memoryA	Delete stored memories. Optionally scope to a tag; with no tag, clears ALL memories in the namespace (destructive).

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/AINative-Studio/ainative-opencode-memory-mcp'

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