gemini-jev-bridge
You can use this MCP server to delegate routine Gemini drafting/analysis and Jev evaluations while Codex remains responsible for planning, review, and applying changes.
Check local Gemini/Jev integration readiness with
bridge_statuswithout paid requests or credential exposure.Delegate one self-contained routine task to Gemini Flash, then have Jev check it against 1–6 explicit criteria; returns a short preview, full result file, and review verdict.
Provide selected absolute file paths and context for delegation; only task text and explicitly selected files are sent to providers.
Ask Jev up to 12 narrow typed questions (choice, boolean-like, score) for routing, ranking, or evidence checks, with optional files and cached repeated evaluations.
Use it for drafting, analysis, code proposals, and advisory Jev scoring; it cannot change source files, browse, or execute commands.
Results are saved locally, exact successful requests are cached in memory for 10 minutes, and live calls consume Google/TypeSafe quotas.
Allows delegating routine tasks to Gemini through a Google subscription in Antigravity CLI, with additional credits disabled.
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., "@gemini-jev-bridge delegate a SQL migration draft to Gemini, then validate with Jev"
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.
Gemini + Jev Bridge for Codex
A local MCP server that lets Codex delegate substantial routine drafting, analysis and code proposals to Gemini. TypeSafe Jev checks the draft against explicit criteria. Codex plans the work, reviews and applies changes, runs tests and gives the final answer.
Gemini uses the included quota of a Google AI Pro subscription through Antigravity CLI. The bridge requires useG1Credits=false: when quota runs out, Gemini work stops until it resets. It does not use a Gemini API key, API billing, credit overages or a paid fallback. Model availability and limits depend on the signed-in Google account and Google's current plan terms.
Jev uses a separate TypeSafe account, API key and quota. It is not included in Google AI Pro. This is an independent project, unaffiliated with Google, OpenAI or TypeSafe.
EN/RU guides
Guide | English | Русский |
Installation, usage and troubleshooting | ||
Setup prompt and instructions for another GPT/Codex chat | ||
Context selection, caching and metrics | ||
Preparing and publishing a clean source export |
Related MCP server: codex-antigravity-mcp
Quick start
You need Node.js 22+, npm, Codex with local MCP support, Antigravity CLI signed in to your Google AI Pro account, and a TypeSafe key. These instructions use Windows/PowerShell; live service access on macOS/Linux has not been verified for this release.
In the repository folder:
npm.cmd ci --ignore-scripts
node setup.mjsEdit the generated settings.json: select an available Gemini Flash model from agy models, set the CLI path and allow only the project folders you need in sourceRoots. Store the TypeSafe key separately in .secrets/TYPESAFE_API_KEY. Then:
npm.cmd test
node smoke.mjs --local-only
node install.mjsReview the installation plan before applying it:
node install.mjs --applyThe installer registers the MCP server, adds delegation rules and restricts the global Antigravity CLI profile, including manual CLI sessions. It backs up existing files. See the user guide for the exact changes and removal steps, then restart Codex.
MCP tools
Tool | Purpose |
| Gemini drafts text or a patch; Jev checks 1–6 criteria; results are saved locally |
| Up to 12 compact routing, ranking or evidence questions per request |
| Local configuration status without contacting the services |
Only task text and explicitly selected files are sent to the providers. Credentials, local settings and generated results stay out of Git. Read the data boundaries and delegation rules before selecting files. Jev scores are advisory; they do not replace review or tests. Delegation still uses Codex for task setup and review, so it does not guarantee a fixed quota saving.
Performance
Select inclusive line ranges with source_selections, give Jev a narrow review_context and mapped review_evidence, and keep the default compact response. Exact successful requests are cached for 10 minutes in memory. Identical concurrent Gemini tasks share one execution; distinct tasks return busy. Full drafts/reviews remain in local artifacts, with timing and actual provider-call metrics. See the performance guide.
Verification
npm.cmd test
npm.cmd run check:publicThese checks and node smoke.mjs --local-only do not call Gemini or Jev. A live node smoke.mjs call uses their quotas and requires completed setup. Passing offline checks does not confirm account access or remaining quota.
License
MIT. Dependencies retain their own licenses.
Available Tools
3 toolsbridge_statusARead-only
Check local Gemini/Jev integration readiness without making paid requests or returning credentials.
Inputs: no named parameters.
delegate_taskA
Send one self-contained routine task to Gemini Flash, then batch-check its result with Jev. Supply selected absolute file paths and explicit acceptance criteria. Returns a short preview, full result file and review verdict. Cannot change source files, browse or execute commands. Uses Google quota and TypeSafe API credits.
Inputs: task (required), review_checks (required), files, context.
jev_evaluateARead-only
Ask Jev 1-12 narrow typed questions for routing, ranking or evidence checks on Codex/Gemini results. Supply context as text/JSON plus optional selected files. Confidence is advisory, not proof or authorization. Repeated identical evaluations are cached in this server process. Uses TypeSafe API credits.
Inputs: context (required), questions (required), files.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools have largely distinct roles: bridge_status is a readiness probe, delegate_task runs a Gemini task with a Jev review, and jev_evaluate queries Jev directly. There is mild overlap since both delegate_task and jev_evaluate involve Jev evaluation, but the descriptions make the boundaries (full delegated workflow vs. narrow standalone questions) reasonably clear.
All names use snake_case, which is good, but the structural pattern is mixed: bridge_status is noun_noun, delegate_task is verb_noun, and jev_evaluate is a namespace-prefixed noun_verb. Readable and not chaotic, but not a predictable verb_noun convention throughout.
Three tools is slightly thin but appropriate for a narrow Gemini/Jev bridge whose scope is status checking, task delegation, and evaluation. Each tool earns its place without redundancy.
The surface covers the core bridge lifecycle: check readiness, delegate a task with review, and run standalone evaluations. Minor gaps exist (e.g., no way to cancel, poll, or manage in-flight delegated tasks), but agents can work around these for the stated purpose.
Related MCP Connectors
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
AI that does the work and checks it. EU-hosted gateway: memory, the codai router, opt-in toolsets.
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables Codex to delegate bounded code analysis, review, isolated edits, multimodal research, and native image generation to supervised Antigravity workers, with queued execution, retries, and inspectable patches.232MIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex users to delegate engineering, refactoring, auditing, and test execution tasks to Google Antigravity CLI as a persistent autonomous subagent, with tools for managing sessions and running prompts.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to delegate heavy coding and image-generation work to Gemini through the Antigravity CLI using a Google AI Pro subscription instead of an API key, while Claude writes briefs, reviews results, and sends corrections. It runs jobs asynchronously in a guarded work folder, continues the same Gemini conversation for fixes, and reports status, output, and token usage back to the caller.MIT
- AlicenseNot gradedqualityBmaintenanceEnables Antigravity to delegate concrete local coding tasks to Codex CLI with durable sessions, background execution, native chat links, and event-driven receipts.MIT