"A calculation evaluating the expression 9999519 plus 9999490" matching MCP servers:

An authenticated OpenAI-compatible inference gateway with an async job broker that bridges a coding agent to a ChatGPT MCP worker, enabling ChatGPT to process inference requests via a tunnel.

Bridges Warp's Oz coding agent to any IDE or MCP client (Claude Code, Cursor, Codex), plus native @oz in VS Code Copilot Chat. Cross-platform (macOS/Linux/Windows), independent project using only Warp's documented public oz CLI + MCP interfaces.

Enables handing one self-contained job to the Claude Code CLI on the local machine and getting back its final message plus a manifest of the artifacts it produced, without letting Claude write into the user's project. Reads are limited to named directories and all writes stay in a throwaway run directory, so the user reviews the listed files and copies in only what they approve.

Shared, code-grounded memory for developers and their coding agents. Capture a learning once and the whole team plus every agent recalls it; memory is grounded in your code and stored as git-tracked JSON reviewed in PRs, with citations validated on write and stale memory withheld from recall. Works with any MCP client.

An MCP server exposing AMPL optimisation modelling to coding agents, plus a matching Claude plugin.

A cross-platform MCP server implementing the Ralph Loop iterative development technique where a worker model does the work and a reviewer model provides cross-model review until approval.

Delegates test writing to a headless second coding agent in an isolated git worktree, then builds, runs the tests, verifies that only test paths changed, and returns a compact report plus optionally applies the verified tests to your checkout. It also flags failures that point to bugs in the production code rather than the tests, keeping test code and terminal logs out of the main agent's context.

Wraps opencode CLI's HTTP API into MCP tools for agent run, session management, and server status, plus a fleet webapp dashboard.

Enables MCP-compatible clients to run reusable, task-specific coding agents defined in Markdown files, executing them through a chosen coding CLI backend and returning results to the same conversation. Supports shared agent, model, and permission configuration plus session continuation across multiple calls.

A server component of the Model Context Protocol that provides intelligent analysis of codebases using vector search and machine learning to understand code patterns, architectural decisions, and documentation.

Enables working a ticket's next unit from your own Claude Code session, where an operator plans, a fenced executor edits your checkout, and the judge verdicts against real git facts. Every edit is approved by you, and the loop resumes or survives interruptions until the ticket is ready or a question is raised.

Enables bounded planner-to-coder-to-reviewer workflows with real file tools and a host-enforced verification gate, using Ollama by default. It supports CLI, TUI, and MCP stdio, plus bidirectional Rose/Neovim editor integration.

Enables users to define task-specific agents in Markdown files and run them through a chosen coding CLI (Codex, Claude Code, Cursor, and others) from any MCP-compatible client, with results returned to the same conversation. Supports shared model and permission settings plus optional session continuity across multiple calls.

Enables users to define reusable Markdown-based coding agents and run them through MCP-compatible clients using a chosen coding CLI backend, with shared model and permission settings plus optional session continuation.

Enables Claude Code and Codex to hand a task to one another as a worker through a single pending MCP call, so the parent agent waits for the result without polling and can resume the same session for corrections. It supports task prompts with working directory, model, effort, and optional trace logging.

Exposes a remote coding agent as MCP tools so an MCP client can delegate tasks, manage their lifecycle, and inspect the agent card, with permission decisions enforced inside the bridge.

Connects MCP-compatible AI clients and agents to one durable Project Brain plus controlled access to authorized project folders on your own machine. Enables file editing, terminal and Git operations, project intelligence, browser automation, and local MCP server federation, all scoped to explicit workspace grants.

Enables querying DeepSeek-Flash with configurable chain-of-thought effort and running autonomous code tasks that plan a spec, edit files, run tests, and self-review the resulting diff. Also provides adversarial code auditing, API health and latency checks, plus workspace, command-blacklist, and Git branch safety guardrails.

Enables users to define task-specific coding agents in Markdown files and invoke them from any MCP-compatible client, running each agent through a chosen coding CLI and returning results to the same conversation. It supports reusable agent definitions with shared backend, model, and permission settings, plus session continuity across multiple calls.

Enables STDIO-compatible AI assistants to queue coding work onto the official Google Antigravity CLI and track status, read reports or patches, query capabilities, or cancel running tasks without blocking. Supports trusted direct execution plus optional isolated or read-only modes depending on the platform.