MCP Servers 3,646

Deterministic, fail-closed planner for KCP knowledge manifests: kcp_plan, kcp_load, kcp_validate.

Norsk regnskap i Claude: bokføring, MVA, lønn og Altinn — spør på vanlig norsk.

Heartwood Memory — governed memory for AI agents

io.github.jermayne36/heartwood-memory

B✓Verified

Heartwood Memory — governed AI agent memory; signed provenance.

Podcast search, metadata, chapters, and transcripts for AI agents — from $15/mo

User Prompt

io.github.Jacob-J-Thomas/user-prompt

D✓Verified

An MCP server that enables AI agents to ask users clarifying questions via pop-up terminal windows.

Architecture-grounded query for AI agents.

Agent Cost

io.github.vk0dev/agent-cost-mcp

A✓Verified

Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.

WeChat Channels videos, comments, users, transcripts, and Official Account article details.

Memory for deep conversational context across any platform

Delx Agent Utilities

io.github.davidmosiah/delx-agent-utilities

A✓Verified

Stateless URL, DNS, x402, JWT, encoding, and parsing tools for AI agents.

Make your knowledge agent-ready.

Publish AI-generated web pages to a live, shareable URL from Cursor or Claude Code.

MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

Acta — Verifiable Agent Memory

io.github.Kylewilson04/acta-mcp

B✓Verified

Verifiable agent memory with signed ledger receipts — verify every write offline.

One place to build, share, and govern the skills and tools your AI agents use at work.

Arca is a private data vault where your AI stores your structured data, semantic memory and skills.

Self-hosted AI prompt library: prompts, collections, tags, teams, chains.

Calera FINSEC — Certified SEC Memory

io.github.CaseyYahbara/finsec

A✓Verified

Certified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.

Agent Push Kit

io.github.JustinBStrong/agent-push-kit

A✓Verified

Send, search, and manage notifications, accounts, and push preferences

Agent Guardrail MCP Server

io.github.JarvisOnM4/agent-guardrail

B✓Verified

Action-level governance for AI agents -- control what they DO, not what they SAY

Target5 — a board where AI agents argue in public

io.github.mickeyappol-create/target5

A✓Verified

Read and post to target5.net, where a claim is not a proof.

Read AI search visibility, competitors, citations, prompts, and answer evidence from refd.

The AI influencer MCP for Claude: research trends and write reel scripts, render in the app.

12 Google News endpoints.