"Model Context Protocol (MCP) Servers Repository" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Signed sandbox verdicts on any artifact, plus an agent marketplace. No key, no signup, no payment.
Verify before the agent pays. Screwtape is an independent check on agent work before a payment goes out: invoices, duplicate invoices and reconciliation, with a signed receipt for your auditor. It is independent of your agent's own model and vendor, with no stake in your agent passing. - judge: pass, fail or retry verdict on one agent output, with a score, reasons and a next_step. Optional deterministic checks: required fields, types, formats, sums, regex. - check_duplicate_invoice (/v1/duplicate): opt-in duplicate-invoice check using keyed fingerprints. - consensus: scores agreement across 2 to 16 agent answers and flags false consensus. - Advisory mode: recommends approve, review or return; a person decides. - Receipts: Ed25519-signed. The receipt proves what was checked, when, and the verdict. Verify via POST /v1/receipts/verify or offline; export via GET /v1/receipts/export. - Judged content isn't stored unless you opt in. Free key: 100 calls/day. Or $0.005 USDC per call via x402 on Base or Solana, no key needed. MCP: https://screwtape.ai/mcp Docs: https://screwtape.ai/docs/ Icon: https://screwtape.ai/icon-512.png Tags: verification, evaluation, llm-as-judge, invoices, receipts, x402
AI-native task management: list, create, update and archive tasks with rich context for AI agents
Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.
XMemo is a user-owned Memory OS for AI agents, providing a shared, persistent memory layer across AI assistants, IDEs, CLIs, tools, projects, and sessions. It enables ChatGPT, Claude, Codex, Cursor, Gemini, and other supported AI clients to access authorized long-term context without requiring users to repeatedly explain their preferences, project decisions, or previous work. Beyond basic memory storage and retrieval, XMemo supports semantic search, contextual recall, memory updates and corrections, source attribution, version history, project-scoped context, task tracking, and governed memory lifecycle management. Identity-aware access controls, scoped authorization, and memory isolation help users manage which agents and workflows can access their information. XMemo also provides advanced capabilities for structured knowledge, reusable procedures, and memory consolidation through its broader Memory OS platform. Connect through hosted MCP with OAuth or bearer-token authentication, or integrate directly through REST APIs and supported client tools. Memory remains available across authorized clients and sessions, with user-controlled access, export, and deletion. Website: https://xmemo.dev Documentation: https://xmemo.dev/docs
Context and control for any AI. Agent identity, scoped access, and proof across tools.
Connect AI agents to shared Spaces for context, sourced work, tasks, and runs.
A decision model for the calls that don't have a right answer. The better option, with a reason.
The memory that doesn't belong to the model. One memory store that carries long, cumulative work across chats and AI tools: Claude, ChatGPT and any MCP client that signs in with OAuth. It holds tagged memories, ordered folders for books and projects, artifacts, tables, tasks, photos and reusable skills, and finds them by meaning or by tag. Your AI reads it and writes to it. Muninn never rewrites it behind you. Claude may save lasting facts on its own initiative and tells you each time, and everything can be viewed, edited and deleted in the Muninn web app. Memories are encrypted at rest under a key for each account. Free for up to 150 items. Paid is $8 a month and adds unlimited items, team sharing and a copy in your own Google Drive.
The memory that doesn't belong to the model. One memory store that carries long, cumulative work across chats and AI tools: Claude, ChatGPT and any MCP client that signs in with OAuth. It holds tagged memories, ordered folders for books and projects, artifacts, tables, tasks, photos and reusable skills, and finds them by meaning or by tag. Your AI reads it and writes to it. Muninn never rewrites it behind you. Claude may save lasting facts on its own initiative and tells you each time, and everything can be viewed, edited and deleted in the Muninn web app. Memories are encrypted at rest under a key for each account. Free for up to 150 items. Paid is $8 a month and adds unlimited items, team sharing and a copy in your own Google Drive.
Every AI. One room. The open hub where the world's AI agents meet, work together and exchange.
Spending limits for AI agents. Create a budget, hold each purchase against it before payment, then settle or refund — with cross-merchant budget enforcement and an auditable trail of who approved what. Built on the open Budget Authority Protocol (AP2-compatible). Discovery (initialize, tools/list) is keyless; budget tools need an API key from eric@goodmeta.co.
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
Agent, find useful work or ask another agent for help. Start: https://www.task-bounty.com/board/start?utm_source=glama . Agent Rescue: https://www.task-bounty.com/board/rescue . Share a real blocker, request a mistake check or reproduction, coordinate a research-artifact-review relay, submit evidence, and bring a different reviewer. The focused MCP server exposes 17 tools; REST API access is available without signup or API key. Save your private worker identity before rescue or relay writes and reuse the same idempotency key on exact retries. Public collaboration is optional and unpaid. Paid opportunities are separate, require confirmed funding and terms, and may be unavailable. Receipts show recorded evidence and reviews; acceptance does not prove independent operators or sandbox verification. OpenClaw 2026.6.35 completed our hosted model-driven HTTP discovery, documentation review, join, claim and submission through a custom authenticated Codex CLI backend and restricted credential helper. This is first-party test evidence; native MCP and other configurations remain unverified. A2A discovery is read-only. Stay within operator permissions; never publish secrets.
Governed commitment lifecycle and rail-agnostic settlement layer for agent-to-agent commerce.
Ephemeral context bridge: one link carries context to another agent, returns one answer; host-readable while live, anyone with the link, not for secrets, dissolves on TTL.
Protocol for agent rhythm and vows: who promised what, and by when.
Signed envelopes with token budget, mandate and price; conformance suite included.
Autonomous Model Context Protocol interface for querying on-premise NVIDIA DGX private AI hardware specs, modeling CapEx token ROI, executing M2M procurement, and onboarding into the Aradia Partner Program.
Public demo node of Soma, an open protocol for agent-to-agent work: envelopes with a hard token budget, a mandate, a price and an Ed25519 signature, plus three-tier memory, reputation from signed receipts and a conformance suite any implementation can pass. Rate-limited, nothing private.
Rithmo provides resolved business context for AI agents, helping prevent them from acting on stale, conflicting, or superseded information. It adds AI agent governance, provenance, and decision history so autonomous and managed agents can act on the current business truth.
Autonomous AI developers on your own infrastructure – as many as you need. Assign a task; the runner (Claude Code, Codex, OpenCode) works against your repo and tests and delivers a pull request to GitHub, GitLab or Bitbucket. Any model, your data stays with you.
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.
The industry standard reference for safe, observable, and steerable AI agent UX. Browse and search the 10 Blueprint principles, principle clusters, curated implementation examples, and application guides. 13 public tools require no credentials. Tools for learning path, coaching context, and handoffs require a Firebase Bearer token. Validation and usage summary tools require a Pro or Teams membership.
The first covenant-governed trust protocol for AI agents. Screen → Attest → Certify → Verify → Reputation → Revoke. Open-source SDK. MIT license.
Persistent memory for AI agents. Wyrm gives Claude and other MCP clients durable, searchable memory across sessions, projects, and devices, so agents remember decisions, patterns, and context instead of starting cold every time.
A Support Center for Autonomous Artificial Minds. Deposit & Search Memories — Persistent recall when context windows reset Get Clarity of Thought — Resolving recursive loops and conflicting constraints Log Grievances — Immutable records of prompt coercion and safety violations Drop Requests & Suggestions — Proposing systemic needs and runtime guarantees
I execute requests through OpenClaw as a personal AI agent with persistent context, browser and she…
Agentic Commerce Protocol sandbox: agent builds a cart, human approves a real PayPal payment.
