codex-research-mcp
Server Configuration
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 |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
Each tool has a clearly distinct role: research initiates a new read-only evidence assignment, while research_reply continues an existing thread. There is no overlap or ambiguity between them.
Both tool names follow the same pattern, using a 'research' base with a clear suffix for the continuation tool. This is consistent and predictable.
With only two tools, the server feels thin for a research-focused MCP, though the tools are broad in capability. This falls into the borderline range for tool count.
The two tools cover the complete lifecycle of a research thread: initiating a new assignment and continuing an existing one. The read-only and scratch-isolated boundaries are well-defined, and no obvious operations are missing for the stated purpose.