A
licenseNot graded
qualityD
maintenanceMCP bridge for calling local coding-agent CLIs (Codex, Claude) from another agent, enabling bounded tasks like code review, verification, and bug hunting.
MIT
Codex Delegate MCP
Related Servers
Alternatives to Codex Delegate MCP
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceBridges Claude Code and OpenAI Codex through MCP, allowing cross-harness querying, code review, explanation, and implementation delegation.64 npm1MIT
- AlicenseAqualityCmaintenanceAn MCP server that splits coding work between ChatGPT web (planning, review) and Codex CLI (implementation), enabling agentic workflows over a local repo with risk-gated execution and safety rails.23MIT
- AlicenseBqualityAmaintenanceLocal-first multi-agent delegation and approval control for Codex via MCP, with persistent task DAG, isolated worktrees, and a web console.181MIT
- AlicenseAqualityBmaintenanceA local MCP bridge that connects existing Codex and Claude Code conversations with DSH Web, enabling delegation, result retrieval, and human-in-the-loop coordination without leaving native chat apps.111MIT
- AlicenseAqualityAmaintenanceBridges multiple CLI coding agents (Codex, Cursor, OpenCode, Claude, Antigravity) into any MCP client, enabling delegation of prompts, parallel execution, and code review workflows.682 npmMozilla Public 2.0
TDQS
A3.9/5.0
Scored across 3 tools
Disambiguation5/5
The three tools occupy clearly separate lifecycle roles: delegate starts work, cancel stops it, and doctor inspects the environment. There is no overlap in intent, and the descriptions reinforce the boundaries (e.g., delegate explicitly forbids shell invocation). Selection risk is low.
Naming Consistency4/5
All three are single-word, lowercase, imperative-style names (delegate, cancel, doctor) with no mixed conventions or prefixes. 'Doctor' is a noun rather than a verb, a minor deviation from the otherwise action-oriented pattern.
Tool Count4/5
Three tools is lean but appropriate for a focused delegation wrapper; each maps to a distinct operation rather than being redundant. The surface is intentionally narrow rather than padded, though it sits near the thin end of the scale.
Completeness3/5
Start (delegate), stop (cancel), and diagnose (doctor) are covered, with resume and review folded into delegate's parameters. However, there is no explicit status/list-runs tool, despite the description telling agents to 'check status before trusting result' — status appears to rely on progress announcements rather than a queryable operation.
Maintenance
ActivityActive
ResponsivenessNo issues