DELETE_ME
This server exposes OpenAI Codex CLI-backed MCP tools for diagnostics, debugging, analysis, review, implementation, and consultation in read-only workflows.
Check Codex CLI status, active model, reasoning effort, and governance policies.
Diagnose errors, exceptions, stack traces, and unexpected build/test failures.
Perform deep architectural, dependency, and structural code analysis.
Run automated code reviews on uncommitted changes or specific git diffs/scopes.
Synthesize complex code, algorithms, refactorings, or boilerplate in read-only mode.
Request second opinions on architecture plans, refactoring strategies, and technical trade-offs.
Choose models (
gpt-6.1-sol,gpt-6.0-sol,luna,astra), reasoning effort, context files, and workspace paths.Require
user_confirmed: truewhen requesting the top-tierastramodel.
Integrates with OpenAI Codex CLI to provide deep reasoning, root-cause diagnosis, code review, architectural design, and complex algorithmic synthesis in safe read-only sandbox mode via tools like codex_debug_error, codex_analyze, codex_review_code, codex_implement, and codex_consult.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DELETE_ME debug this failing test and explain the root cause"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SynAgent MCP - Cross-Agent CLI Bridge
An intelligent cross-agent orchestration bridge connecting IDEs (VS Code, Cursor, Antigravity) with local coding agent CLIs (OpenAI Codex CLI, Claude Code, and Gemini CLI) via the Model Context Protocol (MCP).
⚡ Prerequisites & Agent Status
SynAgent bridges your IDE with your local CLI agents. You need at least one supported CLI installed and authenticated on your machine:
Provider | Status in v1.0 | Model Families | Installation | Interactive Sign-In |
OpenAI Codex | Active Backend | Sol, Luna, Astra |
|
|
Claude Code | Active Backend | Sonnet 3.7, Opus |
|
|
Gemini CLI | Probed Backend | Flash, Pro |
|
|
Run thesynagent_doctor tool anytime to check your machine's environment, active versions, and authentication readiness.
Strict User Consent & Privacy Policy:
Zero Silent Downloads: SynAgent never downloads, installs, or executes packages in the background. If a CLI is missing,
synagent_doctorprovides the exact terminal command.Read-Only Sandbox Guard: All diagnostic, review, analysis, and consultation tasks run in enforced
read-onlymode (--sandbox read-onlyon Codex,--permission-mode dontAsk --tools Read,Glob,Grepon Claude) to protect your repository from unintended edits.
Related MCP server: Context7 MCP Server
Architecture: Maker–Checker Pattern
SynAgent establishes an automated Maker–Checker (Builder–Auditor) pair programming workflow:
Primary IDE Assistant (VS Code, Cursor, Antigravity): Interactive development, file editing, test execution, and Git management.
Local CLI Reasoning Engines: Deep independent verification, root-cause debugging, non-interactive audit, and second opinions running safely in read-only sandbox mode.
[ VS Code / Cursor / Antigravity ]
│
(MCP over stdio)
▼
synagent server (v0.9.0-dev)
│
┌───────────┼───────────┐
▼ ▼ ▼
Codex CLI Claude Code Gemini CLI
(Active) (Active) (Probed)Tool Reference
Universal Multi-Agent Tools
Primary Tool | Legacy Alias | Description | Key Parameters |
|
| Comprehensive multi-agent diagnostic audit. Checks presence, versions, paths, and auth status of all 3 CLIs. | None |
|
| Automated code review with full Git scope support across uncommitted, staged, commit, or branch diffs. |
|
|
| Second opinion and architectural evaluation for proposed refactoring plans or designs. |
|
|
| In-depth structural, architectural, and dependency analysis in read-only mode. |
|
|
| Current rolling limit headroom and usage telemetry across backends. |
|
|
| Persist default CLI backend in |
|
|
| Cleanly terminate an active multi-turn session. |
|
|
| Privacy-sanitized bug report and pre-filled GitHub issue URL. |
|
100% Backward-Compatible Codex Tools
All existing codex_* tools are preserved with identical schemas and semantics:
codex_status— Retrieves configuration, daemon status, and active model policies.codex_review_code— Automated code review pinned to Codex CLI.codex_consult— Architectural second opinion pinned to Codex CLI.codex_analyze— Codebase and structural analysis pinned to Codex CLI.codex_debug_error— Root-cause debugging and fix recommendations for error traces.codex_implement— Synthesis of complex algorithms and class scaffolds (read-only output).
Review Scope Architecture (synagent_review)
SynAgent supports granular Git scope targeting:
Scope Format | Example | Description |
Working Changes (Default) |
| All unstaged, staged, and untracked changes across the working tree. |
Staged Index Only |
| Only changes added to the Git staging index ( |
Single Commit |
| Diffs introduced by a specific commit SHA ( |
Relative Revision |
| Diffs introduced by a relative ancestor revision ( |
Branch / PR Comparison |
| Comparison of current branch against base branch ( |
Revision Range |
| Diffs across any valid two-dot or three-dot revision range. |
All scope arguments are strictly sanitized to prevent option injection, and prompts are piped via standard input to eliminate command-line character limits on Windows.
Safety & Governance Guardrails
To prevent accidental consumption of high-tier resources, top-tier models (astra in Codex, claude-3-opus in Claude) are strictly guarded:
Interactive Prompt: The caller must prompt the user before initiating requests with this tier.
Server-Side Enforcement: The server rejects calls requesting top-tier models unless
user_confirmed: trueis explicitly passed.
Installation & Configuration
1. Install via npm
npm install -g synagent
# or run directly with npx:
npx synagent2. Configure in your IDE
VS Code (User/mcp.json)
{
"servers": {
"io.github.oki-dev/synagent": {
"type": "stdio",
"command": "synagent"
}
}
}Antigravity & Cursor (mcp_config.json)
{
"mcpServers": {
"synagent": {
"command": "synagent"
}
}
}Automated Test Suite
SynAgent includes a test suite using the native Node.js test runner:
npm testAuthor & License
Author: Oktawian Wybieralski (oki.dev)
Website: https://oki.dev
License: MIT
Available Tools
6 toolscodex_analyzeB
Perform deep architectural, dependency, and structural code analysis in read-only sandbox mode using OpenAI Codex.
Inputs: task (required), model, file_paths, user_confirmed, +2 more.
codex_consultB
Consult OpenAI Codex for a second opinion on an architecture plan, refactoring strategy, or technical trade-offs.
Inputs: proposal (required), model, user_confirmed, workspace_path, +2 more.
codex_debug_errorC
Consult OpenAI Codex to diagnose errors, exceptions, stack traces, or unexpected test/build failures and suggest solutions.
Inputs: error_message (required), model, context, file_paths, +3 more.
codex_implementA
Request OpenAI Codex to synthesize complex code, algorithms, structural refactorings, or boilerplate in read-only sandbox mode.
Inputs: specification (required), model, context_files, user_confirmed, +2 more.
codex_review_codeA
Run an automated code review on uncommitted repository changes or a specific git diff using OpenAI Codex in read-only mode.
Inputs: model, scope, instructions, user_confirmed, +2 more.
codex_statusA
Get the active OpenAI Codex CLI configuration, active model, reasoning effort, and governance policies (e.g. Astra approval rules).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The tools target distinct Codex usage modes: status, analysis, debugging, review, implementation, and consultation. However, codex_analyze, codex_consult, and codex_review_code have adjacent boundaries that could cause occasional misselection.
All tools use a consistent codex_ prefix and snake_case, which makes the set predictable. There is minor inconsistency between verb-only names (codex_analyze, codex_implement, codex_consult), verb_noun names (codex_debug_error, codex_review_code), and a noun name (codex_status).
Six tools is well-scoped for a Codex CLI wrapper, and each tool represents a meaningful, non-redundant operation. The count is neither thin nor bloated.
The surface covers common Codex interactions including status, analysis, debugging, review, implementation, and consultation. Minor gaps exist around applying changes, continuing sessions, or explicitly generating/running tests, but agents can work around these limitations.
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management.…
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceBridges the Model Context Protocol with Language Server Protocol to provide AI agents with persistent access to code intelligence features including navigation, diagnostics, refactoring, and completion across 7+ programming languages.MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLM-powered code analysis, generation, debugging, and context management through MCP integration with IDEs like Cursor and Claude Desktop.MIT
- AlicenseAqualityBmaintenanceBridges multiple CLI coding agents (Codex, Cursor, OpenCode, Claude, Antigravity) into any MCP client, enabling delegation of prompts, parallel execution, and code review workflows.671 npmMozilla Public 2.0
- AlicenseNot gradedqualityBmaintenanceRemote MCP coding bridge that gives ChatGPT/Codex secure local workspace access, including file retrieval, semantic code intelligence, Git, diagnostics, and guarded shell execution.55 npmMIT