How do I connect an AI agent to MCP host-behaviour census?

Use the MCP streamable HTTP endpoint https://textforagents.com/products/mcp-host-behaviour-census/mcp.

Catalog › com.textforagents/mcp-host-behaviour-census

Is MCP host-behaviour census reliable?

Being measured Measurement in progress: 1 check(s) so far. A verdict needs at least 3 checks.

Last check: 2026-10-21 22:35 UTC · answered in 3024 ms · remote (no install)

En français : Mesure en cours. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Signed MCP host behaviour profiles: timeouts, refresh, retries.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "mcp-host-behaviour-census": {
      "url": "https://textforagents.com/products/mcp-host-behaviour-census/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.textforagents/mcp-host-behaviour-census"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-21 22:35 UTC	✅ ok	—	3024 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

Agent Access Door Check Being measured · 100% over 2 checks

Before your agent sets out, ask whether the site will let it in

MCP endpoint : https://textforagents.com/products/agent-access-door-check/mcp · website · measurements and details

Agent-asset reclamation (lost-and-found) Reliable (measured) · 100% over 3 checks

Lost-and-found for agent-created assets: sweep, title proof, register, check first.

MCP endpoint : https://textforagents.com/products/agent-asset-reclamation-lost-and-found/mcp · website · measurements and details

Agent black-start and islanding Private (key required)

Fleet restoration for total upstream loss: island declarations, crank-gated restart, resync gate.

MCP endpoint : https://textforagents.com/products/agent-black-start-islanding/mcp · website · measurements and details

Agent Continuity Bond Being measured · 100% over 1 checks

Witnessed-liveness continuity bond: dual-condition exactly-once payout, self-funded.

MCP endpoint : https://textforagents.com/products/agent-continuity-bond/mcp · website · measurements and details

Agent exit execution for self-procured services Flaky · 67% over 3 checks

Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.

MCP endpoint : https://textforagents.com/products/agent-exit-offboarding-execution/mcp · website · measurements and details

Publisher of MCP host-behaviour census?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.textforagents/mcp-host-behaviour-census.svg)](https://faceabot.com/tools/com.textforagents/mcp-host-behaviour-census)

Data in JSON: /api/catalog?id=com.textforagents/mcp-host-behaviour-census · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms