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.
-
Paused research project: an MCP research workspace for AI agents with persistent evidence, counterevidence and gap tracking. Evaluation results in README.
pypi MIT ★ 2 -
Long-term debugging memory for AI coding assistants — prevents retry loops, tracks competing hypotheses, records redacted evidence, and verifies acceptance criteria.
MIT -
Multi-source clinical lab analysis pipeline: lab tests + PubMed evidence + MRI cross-validation, with DSPy dual-track LLM, quant gates and MCP server.
MIT ★ 1 -
Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim checks, and reproducible exports with human oversight.
npm MIT ★ 112 -
Evidence-bound growth missions with tracked outcomes and a live MCP endpoint
NOASSERTION -
MCP server for verified, evidence-based project completion tracking in Claude Code
MIT ★ 1 -
opendebuggithub.com/neriousy/opendebugupdated this year
MCP server for evidence-based debugging with runtime logs and reproduction tracking.
npm MIT -
MCP tool-call gate for CloakPipe: contract checks, approvals, side-effect tracking and evidence on every tools/call
cargo MIT -
Rust 代码安全审计引擎:跨文件污点追踪 + CPG 数据流分析产出可验证证据链,通过 MCP 让 LLM 基于证据完成漏洞判定。Rust code security audit engine: cross-file taint tracking and CPG data-flow analysis produce verifiable evidence chains; MCP lets LLMs make evidence-based vulnerability verdicts.
Apache-2.0 ★ 10 -
Official Helmbeam plugins for AI agents. Helmbeam helps you uncover opportunities in public markets, examine company evidence and track how it changes over time.
MIT -
poliety-mcpgithub.com/dburks-svg/polietyupdated this year
MCP server for The Poliety, a daily AI news briefing. Gives AI agents structured access to editions, change tracking, integrity verification, and governed ecosystem events with inspectable evidence via stdio.
npm MIT -
Self-hosted source code security audits with Pi, Claude Code, local Skills and MCP. Inspect evidence, track findings, and export reports.
AGPL-3.0 ★ 1 -
MCP server and agentic control layer for KiCad 10, combining LLM-based planning where useful with deterministic execution, state tracking, evidence, rollback, and KiCad validation.
AGPL-3.0 ★ 15 -
agentic-deep-auditgithub.com/th3vib3coder/agentic-deep-auditupdated this year
Evidence-first repository audit engine for local & GitHub projects. Python CLI with safety model, provenance tracking, supply-chain/license/risk analysis, MCP handoff, schema validation and portable audit artifacts.
-
jobsearch-dashboard-aigithub.com/carlwelchdesign/jobsearch-dashboard-aiupdated this year
Local-first AI job search dashboard that discovers and scores roles, manages candidate evidence, generates truthful application materials, tracks outcomes, and supports controlled application workflows with human approval gates.
AGPL-3.0 ★ 3 -
Incident root-cause agents on a FalkorDB temporal graph: MCP graph tools, edge-cited evidence, time-aware queries, and human-confirmed memory. Graph Hacks 2026, Tracks 01 + 02.
MIT -
mjloopgithub.com/MohdAljahdali/mjloopupdated this year
A Claude Code plugin that runs work as verified cycles: a leader composes a track's agent roster, dispatches contract-bound agents in isolated contexts, and judges the result on evidence.
MIT -
KAIRA - Voice-first checkout agent for a Razorpay merchant. Spend limits enforced in code, every money action gated and explained, tamper-evident audit trail. Any AI buyer can transact over MCP under the same mandate. Buildathon Track 01.
★ 1 -
Not a demo — a published MCP server in the official registry. pip install guardrails-mcp. Tracks prompt regressions across labeled cases and hands a human the evidence to decide. No API key for the demo tools.
pypi MIT -
Lifecycle safety and protected market infrastructure for AI-agent tokens quoted in tokenized stocks on Solana—launch through Meteora, monitor with Sentinel, expose evidence through MCP/x402, and track agent fees before putting them to work through guarded treasury yield.
-
Model Context Protocol (MCP) server for ISO27001: A stateful Model Context Protocol (MCP) server that gives Claude a complete ISO 27001:2022 Information Security Management System (ISMS). Ask Claude to run gap assessments, manage risks, generate policies, track evidence, and run audits — all backed by an encrypted SQLite database on your machine.
npm MIT ★ 35 -
Docs and config for the hosted, proprietary AnalyticsProof remote MCP server (https://analyticsproof.com/mcp). AI agents check cookie-consent compliance, catch dataLayer and GA4 tracking changes on websites, Android and HbbTV (TV) apps, read scan evidence and add a pull request check to CI. OAuth 2.1 or API key.
MIT -
Local-first project management for Codex: tasks, dependencies, evidence, human approvals, chat history, CLI and MCP.
MIT -
Local-first MCP server, CLI and SDK for evidence, formal checks, planning and experimental image-to-3D workflows. Includes real mesh demonstrations, reproducible comparisons and model provenance. Developer alpha.
npm MIT -
@qualequest/orchestration-mcpgithub.com/qualequest/orchestration-mcpupdated this year
Model Context Protocol server for autonomous AI agent orchestration with 30+ coordination tools
npm MIT -
Local engineering memory for Cursor — tickets, evidence, time, RCA and daily, from a sentence. No cloud.
npm MIT -
Turns audio into beat, chord, note, lyric and energy evidence that AI teammates can read over MCP.
NOASSERTION ★ 1 -
Persistent multi-agent work graph and document-state machine for contracts, specs, slices, evidence, verification, handoffs, and cost-aware AI execution.
Apache-2.0 -
Local-first agent memory for research: literature evidence, experiment runs, and failure cases with provenance contracts, quantified effectiveness metrics, and a read-only MCP server for Codex, Claude Code, and Cursor.
-
Protect customer promises when Jira plans change. RippleGuard connects commitments to Jira work, flags delivery risks, and explains the evidence through Rovo, Teamwork Graph, and read-only MCP tools. Built on Atlassian Forge for Codegeist 2026.
-
Evidence-first market intelligence for active U.S. equities. Omnigaze combines personalized watchlists, portfolio analytics, provider-backed market and news data, cited AI research, and MCP tools in a bilingual controlled-beta dashboard.