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.
-
ai-change-evidencegithub.com/scd13150/ai-change-evidenceupdated this year
Stop AI coding agents from repeating disproven engineering paths. CLI + MCP server for experience handoff.
MIT -
Local search and MCP tools that preserve evidence and detect source or approval changes.
MIT -
Explain changing SEO findings with versioned evidence, deterministic replay, transparent evaluation, and local MCP tools.
MIT -
cb4github.com/borwood/cb4active
The architecture before and after every change, with the evidence in between. A C4 model (LikeC4) your coding agents keep honest: change ledger, governed promotion, evidence-derived verification, via MCP.
npm MIT -
Practice judgment with AI code in VS Code: predict, inspect, and keep or reject changes with evidence. Open source; ChatGPT and MCP support.
MIT -
IronTrellis evidence MCP server: one bounded local tool that copies operator-selected files into an evidence packet when the configured agent still holds the authority, exactly once per operation id. Agents change. The structure holds.
npm Apache-2.0 -
Source-grounded Go intelligence for coding agents: change impact, verification evidence, and coherent context.
go Apache-2.0 ★ 2 -
Deterministic Git & AST change intelligence engine and Model Context Protocol (MCP) server. Detects breaking changes, maps caller blast radius, identifies doc drift, and drafts evidence-grounded release notes with optional local LLM acceleration.
Apache-2.0 ★ 13 -
Dated formula history, confirmed changes, and evidence for U.S. pre-workout supplements.
npm MIT -
MCP server and CLI for b4-after: lets coding agents model a system as C4 (LikeC4), propose and review changes to it, promote accepted changes, and record the evidence that verifies them
npm MIT -
Recommend a semver bump from commit types and API surface changes, with the evidence listed.
npm MIT -
Page Monitorgithub.com/jhfg31410-ai/page-monitor-mcp-serverno update data
Deterministic web page change monitoring with SHA-256 evidence; free diff, paid scheduled watch.
oci -
Deterministic, non-executing evidence and change monitoring for public npm MCP servers. Reports what changed since the version you approved. It never claims a package is safe.
npm Apache-2.0 ★ 1 -
Behavioral diff for AI-written code. Your agent changed 40 files — Veris tells it what behavior actually changed and whether any of it was verified. MCP-native, checker-resolved call graph, tamper-evident evidence. Never executes your code. Local-first, MIT.
npm MIT ★ 2 -
Revnuvo Company Intelligence — evidence-backed technology and infrastructure change signals for AI agents and developers. REST + MCP. Free developer tier: 100 calls/month.
npm MIT -
doneproof-mcpgithub.com/efficjump/doneproof-mcpupdated this year
Evidence-bound completion proofs for software changes through MCP
MIT -
Local-first code graph and change impact analysis for AI coding agents. MCP server, SQLite, tree-sitter. Python and TypeScript. Every edge carries evidence and a confidence label.
pypi Apache-2.0 ★ 1 -
Open-source MCP server and hook service that keeps Claude Code and Codex engineering context current as the code changes, and holds edits whose evidence changed.
npm MIT ★ 12 -
Remote MCP server for verified SaaS pricing: 4,164 tools, source evidence, price-change log
MIT -
Know why Kubernetes broke: evidence-based diagnosis, change correlation and rollback commands. CLI, kubectl plugin, MCP server and Helm chart.
pypi Apache-2.0 -
Give your agent onchain eyes. NEAR account changes, payment evidence and transfer preflight — via chat, MCP & API.
MIT -
Swarm Verify: independent verification for software changes from AI coding agents or humans. Runs a project's real checks, separates what passed from what was established, names what stayed unmeasured, and records evidence anyone can check. CLI, GitHub Action, Claude Code hook, MCP server, pre-commit hook.
ISC ★ 2 -
Local code architecture graph for Python and TypeScript: trace events, contracts, dependencies, and change impact with source evidence.
MIT -
MCP server for managing Thally docs and tracing product changes into evidence-backed updates for human review.
npm MIT -
Span is a local MCP server that keeps the semantic understanding your coding agent worked out — the conclusions, the exact evidence behind them, and what needs another look when that evidence changes. Three tools: ask, record, reconsider.
pypi Apache-2.0 ★ 1 -
Evidence-first local MCP and skills for turning AI research into measured, human-approved setup changes.
npm Apache-2.0 -
Read-only dbt schema-change risk assessment with lineage, verified SQL evidence, guarded agents, MCP tools and reproducible evaluation.
MIT -
🔌 Exposes SOC 2 Type II compliance over MCP — Trust Service Criteria audit, access review, change management, control evidence automation.
pypi MIT -
DecisionGraphgithub.com/hieuchaydi/DecisionGraphupdated this year
DecisionGraph is an engineering decision memory system that captures evidence from GitHub/Slack/Jira, answers “why” questions, and runs pre-change guardrails via CLI/API/MCP.
★ 16 -
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 -
Triage Inbox: Evidence-First Multi-Agent Maintainer Copilot for GitHub PRs — An evidence-first multi-agent system built for the micro1 AI Hackathon that audits software release notes and pull request reviews by grounding every single finding in physical Git commits, diffs, and AST changes before alerting maintainers.
MIT -
Evidence-linked repository change-impact graph with a minimal MCP stdio interface. Unknowns stated as unknown.
MIT -
agent-guardrailsgithub.com/logi-cmd/agent-guardrailsupdated this year
Checks AI-generated code changes before merge: scope, validation, risk, review evidence, and optional Verity receipts.
npm MIT ★ 28 -
Keep code understandable. The evidence layer between the agents that write code and the people who stand behind it: where to look first, who can look, what a change did to the structure and what nobody maintains. Offline, zero dependencies, with the evidence for every claim.
MIT -
Verify code changes with before/after tests and bounded mutation evidence. Local CLI, MCP server and review UI for JavaScript / TypeScript.
MIT ★ 1 -
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 -
tappgithub.com/aarwitz/tappactive
Let coding agents prove UI changes on real iOS, Android, and web surfaces—with inspectable evidence, replayable journeys, and deterministic CI.
npm MIT ★ 4 -
Verify agent-authored change claims at exact Git commits with an evidence-first PR gate and local MCP.
npm MIT -
Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.
MIT ★ 1 -
Local-first repository context for coding agents: codegraph, cited project knowledge, change impact, and evidence-backed workflows.
npm MIT ★ 13 -
Find and verify free-access LLM API routes: dated evidence, browser-direct checks, keyless configs, change alerts, and a read-only MCP server.
NOASSERTION ★ 4 -
Subscription/Renewal Guard — an agent flags price hikes, quiet usage and trial conversions and drafts one action with its evidence; nothing changes until a human clicks Approve. HACK47: OFFGRID entry.
MIT -
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent changes via a macOS app, CLI, and MCP server.
MIT ★ 1 -
m1nd is a local-first context runtime for coding agents: an evidence-bound, continuously verified model of your code, memory, and change.
cargo MIT ★ 24 -
MCP server (2025-11-25, Streamable HTTP): tamper-evident log of what an AI agent did. "Alexa, what did my agent do yesterday, and was the log changed?" Voice simulator + MCP App card.
MIT -
The self-hosted GCP intelligence engine that explains architecture, investigates failures, and predicts change blast radius—with every conclusion tied to inspectable evidence.
go Apache-2.0 ★ 5 -
Local flight recorder for macOS: records app launches, sleep/wake, memory, CPU, battery, network, disk and file changes, and explains them with cited evidence and stated confidence. CLI, menu bar app and a read-only MCP server.
MIT ★ 2 -
Phionyx self-governance gate for Claude Code — three-layer verification (LLM declaration → git diff truth → deterministic gate) over the agent's own 'fixed / tested / changed' claims. v0.3.0 adds opt-in evidence binding: the require_tool directive (a factual claim without same-turn evidence must bind a tool first) and continuity binding (catches 'read-but-not-bound'). Both default-OFF / non-regressive; detector calibration is not yet validated.
pypi AGPL-3.0-or-later -
Local code map for AI coding agents: find, trace, and predict change impact with file:line evidence. Claude Code · Codex · OpenCode · MCP. No network by default.
pypi MIT ★ 13 -
A deterministic code graph for codebases: every caller, route, page and table a change touches, with file:line evidence. CLI, MCP server and web view for AI agents and reviewers.
pypi MIT ★ 4 -
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.
-
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.
go Apache-2.0 ★ 516 -
Index Python, Java, TypeScript and JavaScript into an embedded code graph and answer callers, inheritance, dead-code and change-impact queries with file:line evidence. CLI, MCP server and a labelled retrieval evaluation.
MIT -
Read-only AI SRE for Kubernetes. Finds what's wrong, explains why with evidence, and reports to your terminal or Teams. Never changes the cluster. Bring your own model: Microsoft Foundry, OpenAI, Anthropic or Ollama.
pypi Apache-2.0 ★ 3 -
Decision-Graphgithub.com/tanyasinghp/Decision-Graphupdated this year
Engineering decision memory for your organization. Extract the why behind your code from PRs, issues, and commits, then ask natural-language questions - dg ask "Why was this built this way?" and get answers with evidence chains, not just what changed.
★ 1 -
Local-first project map for AI-assisted programming: scan JS/TS into a feature topology with line-level evidence, expose it to AI agents over MCP, and verify changes against the graph.
MIT -
praxis-datahubgithub.com/Marc-Dvci/praxis-datahubupdated this year
Evidence-bound remediation agent for DataHub-governed data products. Turns one schema-drift incident into a proof-carrying, verified dbt change set — with an MCP server and a DataHub Skill so an agent can drive it, but never approve it.
Apache-2.0 -
The verification layer for AI coding agents. Headron computes what proof each change owes, holds the landing until receipts exist, and keeps the evidence. Any agent, any model, any chat. CLI, MCP, CI.
pypi MIT ★ 4 -
Memory for coding agents. Reverie keeps the engineering conclusions your agent reaches, reviewed by you, grounded in your code and revised as evidence changes, in one local SQLite file. An MCP server: works with OpenCode today; Claude Code, Cursor and Codex coming soon.
Apache-2.0 -
Proves software work: triages failing tests to a cause with evidence, says whether a test could ever fail, breaks your code to see if the tests notice, reads what a migration does to a live database, and gives one verdict on whether a change is done.
npm Apache-2.0