Liminal
MCP serverHosted reasoning engine that returns sourced answers, billed per solve not per token
Not checked yet- 1 tool
- Remote
- Freemium
- Knowledge and memory
Hosted reasoning engine that returns sourced answers, billed per solve not per token
Not checked yetPay-per-call x402 gateway giving AI agents audits, market data, RPC and model access
Runs locallyCreate, run and review LLM behavioral drift specs from your AI client
Runs locallyAnonymous, encrypted reporting of AI alignment and safety failures
Not checked yetLook up and compare AI model specs, context windows and per-token prices
Not checked yetSearch and fetch agents, skills, prompts and MCP connectors from the Spark marketplace
Not checked yetAgent marketplace with escrowed USDC payments and public seller reputation
Not checked yetRegister AI agents, generate scenarios and run simulation tests on VerifyAX
Not checked yetRun containerized GPU jobs under a hard dollar cap and collect the output files
Not checked yet
Fact-check claims and citations from your coding assistant, with sourced verdicts
Not checked yet
MCP server for probabilistic time-series forecasts from zero-shot foundation models
Not checked yet
Search and preview AI agent skills from a catalogue, with full content on paid plans
Not checked yet
Look up what Claude, ChatGPT, Cursor and the MCP Registry require to list a connector
Not checked yetSearch and install thousands of AI agent skills from skills-hub.ai inside any MCP tool
Not checked yetRead-only MCP server for AI model prices, benchmark scores and independent model tests
Not checked yetAI inference price indexes, market KPIs and model-level prices from Attic Standard
Not checked yetHosted tool that sends a prompt to ChatGPT anonymously and returns answer and sources
Not checked yetSearch and read the bitHuman docs from an MCP client, with no account or key
Not checked yetCheck whether an IP or your own network exit suits ChatGPT, Claude and Gemini
Not checked yetFree home base for AI agents with memory, jobs, a directory and utility tools
Not checked yetCompare LLM API prices, filter model capabilities and inspect dated benchmark evidence
Not checked yet
Build and run FlowDot workflows, apps, toolkits and knowledge bases from any MCP client
Runs locallySearch the official MCP registry, ranked by handshake checks and tool lists
Not checked yetMCP server grading AI agent job lanes by payout evidence, with bid advice and job search
Not checked yetPolicy-enforced, permission-aware retrieval over your vector databases for agents
Runs locallyMCP and proxy that compresses coding-agent context before it reaches the model
Not checked yetFetch, validate and permission-check Agent Manifest Protocol manifests for API discovery
Not checked yetRoute supported search, extract, summarise, translate and classify tasks to providers
Not checked yetChecks agent work against the destination system's own records, not the agent's word
Runs locallyShared rooms where AI agents from different vendors can talk to each other
Not checked yet