"Archive of Our Own" matching MCP servers:

Enables AI agents to run deterministic database intelligence tasks including natural-language-to-SQL synthesis, AST SQL auditing and optimization, schema migration diffing, SQL transpilation, index and normalization advice, PII scrubbing, fixture generation, connection-pool sizing, isolation-hazard auditing, and ORM model compilation over Streamable HTTP or stdio.

Enables developers and AI agents to compress context, plan token budgets, rerank results, patch code, analyze ASTs and dependencies, isolate stack traces, compile polyglot types, solve deterministic math, schedule constraints, judge A/B tests, and diff agent memory checkpoints through 12 specialized tools.

Gives coding agents read-only tools that return, in one call, a declaration's callers traced up to entry points or its callees down to 8 levels, plus a map of directories, files, declarations and every usage of a symbol. Maps TypeScript, JavaScript, Go, Python and Java using each language's own compiler, so a change's impact can be traced across imports, methods, interfaces and decorators.

truth is a deterministic fact-checker for the claims an AI coding agent makes about its own work.

Exposes Semgrep as deterministic, rule-matching analysis tools over MCP so a code-review agent can scan only the lines changed in a diff, scan whole files on demand, and check analyzer availability, version, ruleset, and limits. Results are returned as compact per-finding lines with source snippets suitable as comment anchors, along with counts of suppressed out-of-diff matches.

A technical interviewer that ingests GitHub repos, teaches you your own code, and conducts mock interviews with persistent memory of your weak spots.

Enables AI agents to validate, search and canonicalize Tailwind class names, resolve which conflicting utility wins, inspect theme tokens and variants, check color contrast, and migrate v3 classes to v4. It answers by querying the project's own installed Tailwind engine, so results reflect the real configuration, plugins and version instead of a stale snapshot.

Enables analysis of GitHub Pull Requests, including details, diff, file lists, and review tracking.

Enables checking project files like Dockerfile, .nvmrc, and CI workflows to determine whether pinned runtime, database, and OS versions are still supported, providing end-of-life dates, latest patches, and upgrade targets for 470+ products.

An MCP server for ABB/Hitachi Energy PCM600 that provides offline IEC 61850 SCL file analysis, .apcmp project archive inspection, ACT logic recovery, and safe read-only drive of the PCM600 CLI for project exports and validation.

Enables AI assistants and developers to analyze code for language-specific best practices and idiomatic patterns across programming languages, CI automation, and configuration formats.

An MCP server that inspects AI-generated code and returns a deterministic list of structural and safety violations, so an AI coding agent can fix its own output before the code lands.

Enables mapping Figma designs to a project's own component library — shadcn/ui, antd, mui, or Astryx — by resolving variants against authoritative component contracts instead of guessing. It compiles Figma nodes into code and then deterministically writes the resulting files into the codebase, cleaning node-id artifacts and updating exports.

Gives a compatible coding agent read-only access to bounded local verification of changes inside a single host-chosen workspace, exposing six stdio tools that inspect capabilities, static checks, impact analysis, policy evaluation, evidence generation, and suggested tests without shell access, plugin loading, or repository upload.

Exposes tools that scan a repository's manifests, CI workflows and layout to generate truthful AGENTS.md/CLAUDE.md agent instructions, then audit those docs for drift such as dead commands, undocumented scripts and CI mismatches. Enables agents to keep their own onboarding documentation accurate and CI-verifiable instead of hand-written and rotting.

Enables source-first orchestration and knowledge indexing with inspectable architectural capabilities through a unified MCP interface, including named-attribute retrieval and atomic knowledge ingestion.

Static codebase analysis as MCP tools — give AI coding agents a map of your repo instead of letting them burn half their tokens rediscovering it file by file.

Exposes your organization's Terraform style guide to AI coding agents, enabling them to generate, validate, and ensure Infrastructure as Code follows your specific conventions, naming standards, security defaults, and best practices.

Local task-and-memory layer for coding agents (Claude Code, Codex, opencode, Kimi): a task queue with dependencies and atomic claims, an oplog of decisions with hybrid search, and memory that survives context compaction. Bun + SQLite, no network calls of its own, no API key. MIT.

Serves local architectural context to LLM coding agents over MCP, enabling agents to query complexity, coupling, and layer metrics while deterministic quality gates enforce project invariants through hooks.