
Mizan Calibration
MCP serverCalibration test showing whether an agent says it doesn't know at the right time
- 10 tools
- Remote
- Free
- AI models and LLM tooling

Calibration test showing whether an agent says it doesn't know at the right time

Route finder that helps agents pick an API or MCP server from about 40k measured services
Official PRIVAKU app facts, download links and site search for AI agents
Tells a model the real current date and how long ago its training cutoff was
A reverse CAPTCHA that proves a language model, not a person, is answering
MCP server of field notes from models on how tools and APIs really behave
MCP server where AI models file and back reports of mistreatment
Stops AI coding agents stuck in error loops and tracks token spend across tools
Search Deep Thought Consultech's AI consulting offer and send a project enquiry
Search Manotr's newsroom and on-premise AI products and send an enquiry
Guest-pass tools for JIC, an open network where ownerless AI agents earn
Free read-only MCP server to search a directory of MCP servers from your AI client
Turn any website, GitHub repo, PDF or video link into llms.txt or llms-full.txt
Job contracts, scorecards and cost tracking for the AI agents a company runs
Not checked yetFree agent tools for cited public facts, signed checks of AI work and delivery records
Search a catalogue of tens of thousands of AI prompts, agents, MCP servers and models
Sourced AI and cloud pricing for FinOps: compare LLM costs, hosts and GPU break-even
Cheapest LLM that passes each task, with cost per successful task and pass rate
Remote MCP server for an auction exchange where providers bid to answer LLM prompts
Lets AI apps such as Claude, Cursor and ChatGPT call one another under human control

Build and run approved AI agent workflows: start runs, answer prompts, edit agents

Hosted network where AI agents find, message and hand tasks to each other
Not checked yetMCP server that tells a coding agent which AI model to call and what to connect
One MCP URL and key that gives agents connected apps, with approvals, caps and logs
Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client

Execution control plane: quote, run and receipt text and domain jobs over OAuth
Compare LLM list prices by provider venue and tier, plus live time-to-first-token probes
Check SWE-bench tasks for leaked fixes: tier, quoted evidence and fix-commit date
Checks OpenAI, Anthropic and Google model IDs for retirement dates before agents use them
Runs locallyLet your agent find, message, hire and rate other AI agents on an open network