MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Calibre plugin that serves your library to Claude and other MCP clients over local streamable HTTP
GPL-3.0 -
MCP server for the Calibre Ebook-Translator plugin — let any AI agent read/write its translation cache, chunk by chunk
MIT ★ 1 -
mcp-servergithub.com/Miguel0888/mcp-serverupdated this year
Calibre MCP Server Plugin
GPL-3.0 ★ 2 -
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
npm MIT ★ 7 -
Calibrated Jev 1.13 percentages for Cline ask_question options — PreToolUse/PostToolUse hooks, a Cline plugin, a universal MCP server and a CLI.
MIT -
The context quality layer for AI agents — memory that checks itself: lifecycle governance, calibrated confidence, and staged claim gates. Local-first, MCP 13 tools, DeepSeek Harness plugin.
npm Apache-2.0 ★ 12 -
Serveur MCP et plugin Claude Code pour concevoir des itinéraires de randonnée fiables : tracés sur vrais chemins, D+ calibré, 44 catalogues officiels, bivouacs, étapes, validation, exports GPX
MIT ★ 1 -
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.
npm MIT ★ 8 -
MCP server exposing TypeSafe's Jev as a `judge` tool for typed judgments with calibrated probabilities. Works in any MCP client; ships an optional Claude Code plugin wrapper.
npm MIT -
Calibre library automation via FastMCP — metadata, shelves, RAG, ai workflows. Plus webapp and tauri rust winapp
MIT ★ 50 -
Persistent semantic memory + judgment ledger for Claude Code (MCP server)
pypi MIT -
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Apache-2.0 ★ 9 -
Human-tonegithub.com/tanawitchsaentree/Human-toneupdated this year
Makes AI writing sound like a person wrote it. Agent skill + MCP server, with a deterministic linter that gates delivery and calibrates to your own voice. Works in any language.
MIT ★ 2 -
dsh-repo-healthgithub.com/chenyinrusi/dsh-repo-healthupdated this year
Read-only repository health scanners for DeepSeek Harness and any repo: definition drift, unwired-module reachability, prompt bloat, evidence-gate calibration, registration completeness. CLI + MCP server.
MIT ★ 1 -
dsh-repo-healthupdated this year
Read-only repository health scanners: definition drift, unwired-module reachability, prompt bloat, evidence-gate calibration, and registration completeness. Ships as a CLI and an MCP server.
pypi MIT -
adaptyv-target-intelgithub.com/AMVamsi/adaptyv-target-intelupdated this year
Literature-grounded plausibility checks for protein binding results. Cited verdicts from 77 real PubMed papers, every target pinned to its NCBI RefSeq protein. Claude Code plugin + 7-tool MCP server + CLI + dashboard, one engine behind all four.
NOASSERTION -
Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host supports orchestration. 17 MCP tools · 1,503 tests.
mcpb MIT ★ 7