harness-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| codex_queryA | Ask OpenAI Codex a question or give it a task. Use for getting a second opinion, exploring unfamiliar code, or tasks that benefit from a different model's perspective. |
| codex_review_codeA | Ask Codex to review code. Provide a git diff range, file paths, or a code snippet. Returns specific, actionable feedback. |
| codex_review_planA | Ask Codex to critique an implementation plan. Identifies gaps, risks, missing edge cases, and suggests improvements. |
| codex_explain_codeB | Ask Codex to deeply explain code, logic, or architecture. Useful for understanding unfamiliar code, onboarding, or documenting complex systems. |
| codex_plan_perfA | Ask Codex to analyze performance and create an improvement plan. Identifies bottlenecks, proposes ranked optimizations with expected impact. |
| codex_implementA | Ask Codex to implement a feature, fix a bug, or make code changes. WARNING: This modifies your codebase. Returns a summary of what was changed. |
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 6 tools
Each tool has a distinct specialized purpose—reviewing code, explaining code, critiquing plans, planning performance work, and implementing changes. However, codex_query is a catch-all that overlaps with all the other tools, which could create some selection ambiguity.
All tools share the codex_ prefix and use verb-oriented names, making the pattern easy to follow. The deviations are codex_query, which lacks an object, and codex_plan_perf, which uses an awkward abbreviation instead of a clear noun like performance.
Six tools is a well-scoped count for a Codex bridge. Each tool covers a meaningful developer workflow without unnecessary redundancy, and the set feels neither thin nor bloated.
The tool set covers the major interaction modes with Codex: reviewing, explaining, planning, performance analysis, implementation, and general Q&A. The generic codex_query prevents dead ends, though a security-specific review or similar niche tool could be added without much effort.