Schema | Project Oracle

Project Oracle

Describes the environment variables required to run the server.

Name	Required	Description	Default
`ORACLE_DIR`	No	Root directory for all Oracle state	~/.project-oracle
`ANTHROPIC_API_KEY`	No	Required only for oracle_ask Haiku fallback

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`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
oracle_readA	Read a file, returning full content on first read or a compact delta on repeat reads.
oracle_grepB	Search source files for a regex pattern. Returns up to 50 matches.
oracle_statusA	Return current project status: stack info, git branch, clean/dirty state.
oracle_runB	Run allowlisted commands through the cache layer. Returns cached results when unchanged.
oracle_askC	Ask a natural-language question about the project. Routes to cache, grep, or Haiku.
oracle_forgetA	Clear the file cache for a path. Next oracle_read returns full content.
oracle_statsA	Return token savings stats for the current session and cumulative across all sessions.

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/mikelane/project-oracle'

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