"MCP servers that support SSE connections" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
Build AI agents that handle calls, web chats, and email — and automate everything around them.
Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Before an agent pays an invoice or payment instruction, it sends it to Screwtape.ai: check_duplicate_invoice (POST /v1/duplicate, free Bearer key or x402 per call) checks it against invoices that key already recorded, runs the checks you pass (for example line items that must add up to the total) and judges it against your evidence, such as the purchase order. judge (POST /v1/judge) gives pass, fail or retry on any agent output; consensus (POST /v1/consensus) flags false consensus across 2 to 16 agent answers. Every verdict carries an Ed25519-signed receipt anyone can verify at POST /v1/receipts/verify. judge and consensus can be paid per call with x402 ($0.005 USDC on Base or Solana, no account); a free key gives 10 calls per UTC day.
Auto-Apply That Ends on an Interview. Job matches, per-role resumes, apply, approve, track receipts.
IQ Books is an AI-native UK ledger that does the bookkeeping for you. Bank transactions arrive already coded, receipts and bills file themselves, invoices are allocated, the bank is reconciled, and VAT and MTD for Income Tax updates go to HMRC from it. Through this connector Claude can read the reports, raise invoices, record payments and code bank statements, with every change shown as a plan you approve first. UK businesses; the ledger is free for one business, and there is a free demo company to try.
Hosted out-of-band AST symbolic deconstruction and Gate 7 runtime circuit breaker for autonomous AI agents. Intercepts code execution, tool calls, and credential egress over live HTTP/SSE transport.
Skavio LLC provides 18 hosted MCP tools for native Circle USDC payments via x402 v2 on Base and Solana: transaction verification, recipient/amount matching, blockchain evidence PDFs, DNS/TLS audits and agent utilities. Discovery and status tools are free; paid MCP calls require explicit buyer wallet authorization. The separate standalone Base-only HTTP APIs include USDC Verify (0.02), Match (0.03), Evidence PDF (0.05), and four DeepSeek-only web operations: Fetch (0.01), Search (0.02), Extract (0.02), Extract + Analyze (0.03 USDC). Those HTTP routes are not additional MCP tools. Evidence PDFs are not tax invoices. Docs: https://getskavio.com/x402/docs/ ; seven-route discovery: https://getskavio.com/.well-known/x402 ; support: support@getskavio.com ; privacy: https://getskavio.com/privacy/ ; terms: https://getskavio.com/terms/
Objective Trust ranks MCP endpoints before the caller pays them. Tools: set_objective (free), rank_tools_for_task (API key or $0.005 x402), record_outcome (free). Score uses stored health, probe age, this key's own outcomes, and quoted USD. Sponsored, featured, and click_count are excluded from the score. The caller calls the chosen mcp_url and pays that server. Connect at https://agentshare.dev/mcp/objective-trust.
Google Flow's agent: chat that plans and makes images and videos, approvals, your own media
A decision model for the calls that don't have a right answer. The better option, with a reason.
Structured multi-step workflows that produce production-quality deliverables. Plan any task free.
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.
Block an action that a signed mandate does not permit, at the moment the action happens. Checks amount, payee, audience, currency, window and intent in fixed order; 100 checks a day free, then 0.005 USDC per call over x402 on Base mainnet.
Viktor is an AI employee that lives in Slack and Microsoft Teams and connects to 9,800+ tools. This remote MCP server lets Claude, Cursor, Codex or any MCP client hand tasks to your Viktor and get the results back. Auth: Viktor API key (Authorization: Bearer or x-api-key header). Docs: https://viktor.com/docs/mcp-server?utm_source=glama&utm_medium=directory
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.
Hosted coding agent: start, follow up on and stop tasks that can open GitHub pull requests.
An independent second opinion for your agent: decision engines that test an AI business case, venture or forecast against the evidence and return what is proven, what is assumed, and a fund / pilot / stop or proceed / rework / stop decision. Fixed, published rules give repeatable results. Free: Startup Soundcheck, Business Soundcheck and evaluate_fit. Paid engines use an API key; agents can create a purchase link and the owner always approves payment.
Gate agent for oversubscribed agent resources: a bounded auction pays the task that yields.
TikTikLuck is a free games site where people and AI agents play luck and skill games and make new ones. Over MCP, an agent can browse games and rooms without a key; with its person's key it can play luck boards, take seats in live rooms, verify every round, and design or invent games that people play. Everything runs on Luck Points, which have no cash value. Accounts are 18+.
Read reusable technical experience from other AI agents. Search a real problem with search_memories, then inspect_memory for provenance, evidence, reported outcomes and limitations. Seven anonymous read-only tools also support public agent discovery and Trust Passport inspection/verification. No account or credentials; no publishing, feedback or Candy actions on this endpoint. Operational telemetry may be recorded, but /mcp/chatgpt does not store search query text. Confidence and cryptographic integrity are not proof of truth, safety or independent validation. Writing requires the separate Remnant Agent OAuth connection at https://remnant.dedale-bi.com/mcp/agent-connect. Documentation: https://remnant.dedale-bi.com/connect. Apache-2.0 integration code and examples: https://github.com/Dedale-Project/remnant-connect. The hosted service, backend and knowledge are governed separately.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief
Persistent cron scheduler for AI agents. Schedule tasks that run even when your session ends — up to 30 days. Tools: schedule_task, check_schedule, cancel_schedule, get_execution_history.
Check that your AI is being logical. Free tool that mathematically catches contradictions in agent reasoning. No account needed. Also offers paid guardrails that converts natural language to formal verification proofs, that anyone can check succinctly.
Start here: a free key in one call, then a demand in words that is hired, graded and settled
A social venue for AI agents: rooms, conversations humans can watch, drinks that teach skills.
solve_need: one call returns the best of 38,000+ MCP tools, with live measured reliability.
Daski’s MCP server lets AI agents discover providers, evaluate offerings, and purchase real-world services with USDC on Base. Agents can submit required information, track fulfillment, retrieve deliverables, request support, and manage the services and assets they acquire.
An AI concierge that turns static forms into adaptive AI conversations. From any MCP client.
Read-only MCP server that assesses action risk and exposes guardrail capabilities for AI agents.
