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.
-
serverless-decision-log-mcp-servergithub.com/akamai-developers/serverless-decision-log-mcp-serverupdated this year
A Serverless MCP Server built using wasmcp, Spin and Akamai Functions
★ 4 -
vibe_coding_enhancedstale
MCP server for managing Agent Important Decision Log (AIDL) in Vibe Coding workflows
npm MIT -
Log, evaluate, and ground every consequential AI-assisted decision against your organization's authority graph. Traceable decision audit trail. Developer tier free.
MIT ★ 1 -
@tonytangdev/logdgithub.com/tonytangdev/logdupdated this year
CLI tool & MCP server for logging and semantically searching decisions using local LLM embeddings
npm MIT WITH Commons-Clause -
@geshtu/mcpgithub.com/crowditory/geshtuupdated this year
MCP server for Geshtu — self-hosted shared memory for teams using LLMs. Exposes 6 tools (search, decisions, digest, log_decision, log_fact, close_session) that proxy to a self-hosted memory-api.
npm AGPL-3.0-only -
waypointgithub.com/alejandramantillac/waypointupdated this year
Distills the architecture decisions buried in your coding agent's session history into a navigable log.
MIT ★ 1 -
depositiongithub.com/georgedagher/depositionupdated this year
Local-only decision log for AI agent sessions -- zero API calls, deterministic decision extraction.
MIT ★ 1 -
Holds risky AI agent tool calls for a person, ties each approval to one exact request, and logs every decision. 210 checks, synthetic data.
MIT -
Drop-in recorders for Python and Node, plus a local MCP server, that keep each decision record in your own journal and seal only its salted SHA-256 in a tamper-evident evidence log.
Apache-2.0 -
Authorisation-bounded execution for AI agents that run security tools: an engagement file, a scope engine, a fail-closed decision matrix and a hash-chained audit log, with a CLI, a Claude Code hook and an MCP server example.
Apache-2.0 -
A permission layer in front of MCP tools, and a log that can prove why a call was allowed. Naive: 7 calls execute with no grant, 16 decisions cannot be reconstructed. Guarded: 0 and 0. Offline, zero deps, MIT.
MIT -
MCP stdio server for agents to record their decisions history in a tamper-evident JSONL log
MIT ★ 4 -
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
npm AGPL-3.0 ★ 162 -
Safety-first clinical decision-support research agent: auditable state machine, Bayesian differential ranking, 300 deterministic medication-safety modules, FHIR R4, durable audit log and a dual-era MCP server for Claude, Cursor and VS Code. Research use only, not for clinical deployment.
NOASSERTION ★ 4 -
MCP server over my AI ticket triage queue: four read-only tools for the queue and human decision log
MIT -
A lightweight task framework — persistent task tracking, memory injection, and structured decision logging via MCP tools.
★ 1 -
Defygithub.com/ASIKKANI/Defyupdated this year
An MCP-powered autonomous AI trading agent that executes crypto trades via smart contracts while logging every decision on-chain for full transparency, auditability, and trustless AI–Web3 integration.
★ 1 -
agent-reflexion-mcpgithub.com/mdfifty50-boop/agent-reflexion-mcpupdated this year
Agent self-improvement and reflection MCP server — decision logging, pattern analysis, performance tracking
-
@glidepaths/mcp-servergithub.com/jossiekc/lucid-ai-lawsupdated this year
MCP server for Glidepaths AI governance — log decisions, evaluate actions, and query compliance posture from any Claude-powered agent.
npm MIT -
mcp-credit-bureaugithub.com/zavora-ai/mcp-credit-bureauupdated this year
Credit Bureau MCP Server — a credit-reporting platform (consumers, credit reports with tradelines/inquiries/public records, scores and factors, permissible-purpose-gated report pulls that log a hard inquiry, FCRA disputes, monitoring alerts, and affordability/decision analytics) with FCRA-style permissible-purpose enforcement and full access logging
cargo Apache-2.0 -
Project memory across sessions for AI agents. A queryable decision log that survives between sessions, so agents remember what was decided and why.
npm MIT -
Fast, cheap browser actions for agents: a decision model (Jev or Clef) drives your real, logged-in Chrome. CLI + MCP server.
npm MIT -
Fast, cheap browser actions for agents: a decision model (Jev or Clef) drives your real, logged-in Chrome. CLI + MCP server.
npm MIT -
Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
MIT ★ 1 -
Recover the why behind a codebase: mine git history, PRs, issues and comments into a browsable decision log of ADRs, with an MCP why() tool for agents.
MIT -
Session state persistence for MCP systems. Crash recovery, decision logging, context compression for AI sessions. (Companion repo — architecture and interface only. Source lives in the private engine.)
-
hermes-memory-mcpgithub.com/nauta-ai/hermes-memory-mcpupdated this year
Local-first MCP server that gives AI coding agents persistent, cited memory of their project's notes, decisions, commits, and logs.
pypi MIT -
MCP server for PM Groundwork - persistent project memory, decision logging, session rituals, and PM document drafting for Cursor, Codex CLI, and Gemini CLI
npm MIT -
🔌 Exposes Hash-chained HMAC-signed audit log over MCP — for A2A (agent-to-agent) calls. Every tool-call, agent-handoff, decision gets a tamper-evident signed record. EU AI Act Art 12 automatic logs, DORA Art 17 ICT incident logs, ISO 42001 clause 9 monitoring — auditor-ready end-of-day attestations. By MEOK AI Labs.
pypi MIT -
Local ClickUp CLI/MCP server for agents: dry-run-first generated V2 operations, curated workflows, GitHub dev sync, work logs, decisions, and handoff context.
Apache-2.0 ★ 1 -
Visual project planning tool — Kanban board, wiki, workflow canvas, architecture view, timeline & decisions log in a glassmorphic UI
npm NOASSERTION ★ 4 -
leonardgithub.com/jasondillingham/leonardupdated this year
Local-first ground-truth toolkit for Claude Code: symbol index + decision log + claim ledger over MCP and hooks.
go Apache-2.0 ★ 1 -
Model Context Protocol server exposing Arbor design system tools: Playroom snippets, Figma→code sync health, UX-writing checks, decision-log lookup, and federated component/version metadata.
npm UNLICENSED -
A merchant's transactability layer for AI buyers: MCP-callable Razorpay commerce with signed spending mandates, an audit log of every decision, and a benchmark measuring agent transaction success vs. a plain storefront.
MIT -
MCP server exposing autonomous-audit's tamper-evident decision log (record/verify/report/anchor) as agent-callable tools - integrity & traceability for AI trading agents (not investment advice).
pypi Apache-2.0 -
cairngithub.com/juw12/cairnactive
A second brain that lives inside your repo, as plain Markdown next to your code: ideas wall, task board, decision log, offline voice log, a live dashboard of your AI coding sessions with progress, time left and effort, phone pairing by QR, chat with your own AI models from anywhere, an MCP server and an autopilot. Zero dependencies.
mcpb MIT -
MCP server for million, the open-source self-hosted Solana whale tracker and copy-trading deck: status, positions, decision log, trading rules, order flow, token checks and whale discovery.
npm MIT -
MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.
MIT ★ 1 -
buzz-axirugithub.com/axiruai/buzz-axiruupdated this year
Bounded spend authority for Buzz agents. A gating MCP proxy in front of your payment MCP server: policy evaluation before money moves, human approvals in the Buzz channel, and a hash-chained decision log keyed to the agent's Nostr pubkey.
npm Apache-2.0 -
@tessera-llm/mcp-servergithub.com/tessera-llm/mcp-serverupdated this year
MCP server exposing Tessera's LLM cost optimization layer as tools for Claude Desktop, Claude Code, Cursor, Cline, Continue, and other MCP-aware clients. Returns savings decisions (anchored spend, drift detection, recommendation approval), not raw logs.
npm Apache-2.0 -
MCP server mang quy trình làm việc theo wave giữa PO và AI vào mọi dự án: Orchestrator điều phối, bộ phận lập theo dự án, decision log, quality gate, nâng cấp bằng three-way merge.
pypi MIT ★ 1 -
pgguard-mcpgithub.com/Azzaraell/pgguard-mcpupdated this year
Read-only MCP server for Postgres. A deny-by-default policy file decides which tables and columns an AI agent can see; every query runs inside a BEGIN READ ONLY transaction with a statement timeout, and every decision lands in an audit log.
MIT -
Pre-commitment check for film and TV production. When tomorrow's call sheet is issued, it checks every scene scheduled to shoot against the current script revision, the film's established facts and the production's logged decisions — ranked by what has already been paid for. Gemini + ClickHouse via MCP.
MIT -
revenue-engine-demogithub.com/robipowers/revenue-engine-demoupdated this year
Lead routing engine for B2B inbound: fuzzy lead-to-account matching, enrichment, a propensity model and territory routing, with human approval before any lead is assigned. Every decision lands in an audit log, and an MCP server exposes the DuckDB warehouse to agents. Runs offline in seconds, backed by 129 tests.
-
Memolok is the Decision Record platform. It records decisions as Memolok Decision Records: structured, immutable entries capturing the need, the alternatives, and the reasoning behind a choice. Plugin for Claude and Claude Code.
★ 1 -
Model Context Protocol (MCP) server for Decision Keep's out-of-band forensic witness. Lets AI coding assistants, agents and orchestration frameworks natively verify decision trails without pipeline latency.
npm MIT -
Keep decision records in Git and see which ones a code change touches, in pull requests and through AI agents.
Apache-2.0 ★ 2 -
The project's decision graph for AI coding agents: decisions, rejected alternatives and gotchas, anchored to your code.
pypi Apache-2.0 -
Project-state MCP server for Claude Code and Codex: every AI decision visible, traceable, revocable.
-
Reasonbook: decisions that survive the session, in a local record AI agents keep.
npm Apache-2.0 -
Your team's decisions, briefed to every Claude Code session before it writes code.
npm Apache-2.0 ★ 12 -
Local memory of past decisions for Claude Code and Codex. Records sessions and decisions in a local SQLite file and recalls them over MCP.
MIT ★ 1 -
project-memorygithub.com/hozakar/project-memoryupdated this year
Engineering decision memory for AI-assisted coding — captures the why behind your code
MIT -
kontrol-freek-mcpgithub.com/berkbayri/kontrol-freek-mcpupdated this year
AI assumption firewall for MCP agents — intercepts risky decisions, checks past decisions, detects contradictions, and gates human approval via Telegram or Slack.
pypi ★ 1 -
MIRSAD (مِرصاد) — a shared, living memory hub for AI agents: bi-temporal facts, first-class decisions, owner-resolved conflicts, and a live graph view. Local-first
pypi MIT ★ 2 -
Docs site for your ADRs and RFCs, straight from Markdown in your repo. One repo for every team, full-text search, Mermaid, filters by team, tag and author, a decision graph, review reminders and an RFC process. Static output, no server or database. MCP server and llms.txt so your AI tools know why things are the way they are.
MIT ★ 2 -
A local wiki your agents write for you. Nimbalyst Wiki plugin for Claude Code and Codex: capture decisions, track typed pages, read and edit in your browser.
MIT ★ 36 -
@nikheal/devstate-mcpgithub.com/nikheal-patel-dev/devstateupdated this year
DevState MCP server — gives Claude, Cursor, Windsurf, and any MCP-capable AI assistant portable, persistent project context.
npm MIT -
Local decision ledger for AI coding agents — keeps why a choice was made and which paths are dead ends, and re-injects it after context compaction. Plain Markdown, zero dependencies, works across Claude Code / Codex / Cursor / Copilot / Gemini.
MIT -
Cognitive middleware for personal and enterprise AI agents: 14 MCP tools and a REST API for intent mirroring, persona/context profiling, decision support, memory, guardrail checks, and approval workflows. Deterministic offline engines with optional live Jev, SQLite/PostgreSQL, and Docker.
MIT ★ 1