mcpcost

io.github.enzoduit/agentfabric

AgentFabric — Human-in-the-Loop Review & Approval

Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.

alive probed 2026-10-05 · HTTP 200

1tools
237tokens in Claude Opus 5.5
247tokens in Claude Code
0.1 %of a 200k context window
127o200k_base estimate
851 msto initialize
250 msto list tools
Endpoint
https://mcp.agentfabric.dev (streamable-http)
Host
mcp.agentfabric.dev
Protocol
2025-11-25
Reports itself as
agentfabric 0.1.0
Capabilities
tools
Instructions
194 characters
Claude count
Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
Registry
active, updated 2026-08-10 · registry entry
Reachable
6 of the last 6 probes

Most expensive tools

ToolTokens (o200k)Share of this server
create_tenant127100 %

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-05 14:43alive851 ms1237127
2026-10-05 00:34alive845 ms1127
2026-10-04 10:04alive1.6 s1127
2026-10-04 07:58alive1.7 s1127
2026-10-03 20:37alive2.0 s1127
2026-10-03 17:53alive264 ms1127

Badge and feed

mcpcost: alive

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.github.enzoduit/agentfabric.svg)](https://mcpcost.ulehla.dev/s/io.github.enzoduit/agentfabric)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.