mcpcost

io.github.naoanao/safe-agent-mcp

Safe AI Agent Guard Checks

Is the io.github.naoanao/safe-agent-mcp MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-11.

Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.

alive probed 2026-11-14 · unchanged since 2026-11-11

3tools
571tokens in Claude Opus 5.5
0.3 %of Claude's 200k window
0.2×the median server
2.4 sto initialize
417 msto list tools
Run it
uvx safe-agent-mcp@0.1.0 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
Safe AI Agent Guard Checks 4.1.8
Capabilities
logging, prompts, resources, tools
Instructions
none
Of a 1M window
<0.1 % of a 1M context window
Count
571 tokens in Claude Opus 5.5, exact, measured 2026-10-29. With the Claude Code prefix mcp__…__ on each tool name: 613. The o200k_base estimate is 306. Counted again when the tool definitions change. Method.
Repository
https://github.com/naoanao/safe-agent-mcp
Registry
active, updated 2026-10-29 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.87×.

Tool≈ Claude tokenso200k estimateShare of this server
audit_api_keys24613243 %
check_idempotency_pattern1759431 %
explain_guard_pattern1498026 %

Compare this server with others.

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention safe.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher