"The number 555" matching MCP servers:

Lets AI coding agents read an outline of a large file or a digest of noisy command output instead of the full text, while every hidden line stays retrievable on disk through a run handle. Agents can request only the line ranges, slices, or grep matches they need and list recent runs, cutting token spend without losing information.

A local stdio MCP server that lets a coding agent verify its compute environment, trace Python and QuantLib pricers without code changes, and interrogate the resulting tapes for constants, near-flipping decisions, source lines and exact replays at new inputs. Every reported number and file:line is produced by the engine itself, with the agent narrating rather than computing.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

Exposes 11 agent-native QA tools over stdio so coding agents can discover a project, analyze risk, select the smallest relevant test set, generate and dry-run tests, triage failures, propose tiered heals, analyze flakes, generate quality reports, and evaluate release readiness. Planning and healing tools stay read-only or propose-only, while execution defaults to dry-run, keeping agent actions safe and evidence-backed.

Provides AI assistants with progressive code intelligence to explore repository structure, find symbols, and assess the impact of changes using ast-grep.

Enables querying any GitHub, GitLab, or Bitbucket repository and getting AI-generated answers about the codebase, powered by Gemini.

Enables asking natural-language questions about any GitHub repository and receiving answers grounded in the actual code, with read-only enforcement and automatic repository fetching.

Enables AI coding agents to list, read, create, update, delete, and render PlantUML and Mermaid diagrams, and check them against the actual codebase to detect architecture drift.

Enables Claude Code agents and subagents to get an independent read-only review of their changes from OpenAI Codex and to continue that same Codex conversation later for re-checks. Runs each request in an isolated CODEX_HOME so those threads stay separate from the Codex desktop app, supporting parallel callers and per-call model, effort, sandbox, and timeout settings.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

Aegis keeps Claude Code, Codex CLI and Antigravity on your project's rules via a zero-dependency Model Context Protocol (MCP) server (aegis-mcp), AGENTS.md / CLAUDE.md bootstrap, git pre-commit hooks, and CI governance (aegis check). It serves each agent just-in-time rules for the files it is about to edit, then enforces AST and repository invariants before commit and in pull requests.

Compiler introspection for the Hirð language (typed actors and effect rows on the BEAM): type inference, definition lookup, effect-row explanation, IR fragments, actor protocol and supervision graphs, and token-budget-aware symbol summaries.

myopic is a code-review MCP server that reviews GitLab/GitHub merge requests against the whole codebase, not just the diff, analyzing blast radius and conventions.

Enables read-only access to the canonical-vault GitHub repository through MCP, letting clients list files, retrieve file contents and history, inspect commits, and search code.

AI code review against your team's own rules from your repository, before the pull request: two tools, review_changes and get_team_rules. Closed-source binary distributed via GitHub Releases; published in the official MCP Registry as dev.reviewgate/reviewgate.

Enables Claude Code to hand off mechanical work — file edits, code lookups, and lint triage — to a local Ollama model that reads and edits files directly, so file contents never enter Claude's context. Returns only a compact receipt, and reports success only after the change passes a deterministic syntax/project gate, rolling back and escalating on failure.

Indexes codebases cut at function and class boundaries into Oracle AI Database 26ai, letting AI coding tools search code by name or meaning, trace callers, callees and change impact, read per-module wiki pages, and recall facts from earlier sessions. All of it is served over the Model Context Protocol with embeddings computed in-database, so no source code leaves the machine and no API key is required.

C++26 paper reference MCP with lookup_paper, fuzzy search, and compiler_status tools over a 216-paper ISO/IEC 14882:2026 corpus. Backs a Claude Code plugin that biases the model toward final-form C++26 idioms (reflection, contracts, std::execution senders, expansion statements, #embed).

Enables AI coding tools to run CheckMyLaunch scans on GitHub repos or live URLs and retrieve findings and repair prompts directly within the chat.

A production-ready Model Context Protocol (MCP) server that bridges your Symfony/PHP project with LLMs such as Claude. It exposes tools that let the AI read your project's routes, services, Twig templates, and PHP source code.