"Writing about MCP" matching MCP servers:

Extracts deterministic architecture maps from codebases for AI agents, enabling queries about blast radius, routes, security findings, and production readiness without sending code anywhere.

An MCP server that lets AI agents drive FigJam boards through a local Figma plugin, bypassing API rate limits with 19 tools for reading, writing, and editing FigJam content.

Enables AI coding agents to make evidence-aware design-pattern decisions by analyzing cases, comparing options, detecting misuse, stress-testing assumptions, planning adoption, writing ADRs, and generating evidence plans with transparent scoring.

Enables AI assistants to understand and analyze Spring Boot codebases through static analysis, allowing natural language queries about endpoints, classes, dependencies, and architecture without running the application.

Infers the architecture rules a TypeScript repo already follows from its import graph, with the evidence for each rule. Read-only tools to scan, recommend and explain rules, so an agent can check them before writing code.

Enables AI agents to generate BYaML Architecture Graphs from evaluations, Terraform plans, and AWS scans, and to derive insights such as blast radius, cost summaries, and remediation plans without writing YAML.

Indexes a workspace into a graph of files, modules, symbols, SQL tables, API contracts, and CI/container files, then answers questions about it. Enables querying dependencies, affected tests, blast radius of a change, node focus, and diffs between refs, all read-only and within a configurable byte budget.

Enables AI agents to query a repository's verified semantic model, including capabilities, ownership, contracts, constraints, impact, health, and verification status, without re-deriving project facts. It exposes read-only tools for inspecting, reasoning about, and verifying the provenance-tracked surface.

Enables Claude to turn a public or private code repository into an interactive, in-chat graph of its folders, files, classes, functions and API endpoints, including the calls, imports, tests and HTTP requests linking them, which users can pan, search, filter and click through. Provides tools for exploring a node's callers, callees and tests, searching nodes by name, path or docstring, and optionally writing the graph into Neo4j.

Publishes eight tools that let an AI coding agent declare an entire layered dependency design as ghost nodes before writing code, then light each node up as it is built and verified—with a spinner on the current node and reddening when later work cracks a foundation. This gives developers a live, terminal-side view of bottom-up progress where upward edges and duplicate ranks are refused, so a bad design can be vetoed while it is still only a picture.

Builds a dependency and topology graph of a Kubernetes/FluxCD GitOps repository via static analysis, enabling AI agents to reason about service relationships without cluster access.