Schema | codex-research-mcp

codex-research-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CODEX_RESEARCH_CODEX_BIN`	No	Codex executable	codex
`CODEX_RESEARCH_STATE_DIR`	No	Scratch and authorized-thread state directory	<system temporary directory>/codex-research-mcp
`CODEX_RESEARCH_SOURCE_ROOT`	No	Default readable source root when a tool call does not provide source_cwd
`CODEX_RESEARCH_MAX_CONCURRENCY`	No	Simultaneous Codex calls	4
`CODEX_RESEARCH_TIMEOUT_SECONDS`	No	Per-call timeout	3600

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
researchA	Delegate one read-only evidence assignment to Codex for discovery, retrieval, extraction, organization, comparison, calculation, or verification. The real source tree stays read-only; downloads, scripts, and intermediate files are confined to a private temporary scratch directory. Independent calls may run concurrently.
research_replyA	Continue a research thread previously created during the current MCP server lifetime. The original scratch isolation and source boundary remain in force.

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/pku-zhb/codex-research-mcp'

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