io.github.msaad00/agent-bom
agent-bom
Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.
alive probed 2026-10-19
8tools
≈ 4.3ktokens, estimate
≈ 2.2 %of Claude's 200k window
3.0×the median server
5.4 sto initialize
10 msto list tools
- Run it
- uvx agent-bom==0.109.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- agent-bom 0.109.0
- Capabilities
- prompts, resources, tools
- Instructions
- 642 characters
- Of a 1M window
- ≈ 0.4 % of a 1M context window, estimate
- Claude count
- The count_tokens endpoint refused the tool schemas: invalid x-api-key. The estimate stands in.
- Repository
- https://github.com/msaad00/agent-bom
- Registry
- active, updated 2026-10-18 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| scan | 1 759 | 41 % |
| exposure_paths | 715 | 17 % |
| check | 498 | 12 % |
| compliance | 476 | 11 % |
| remediate | 261 | 6 % |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
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
- The Anthropic count_tokens endpoint refused the tool schemas (invalid x-api-key). A client that validates schemas can refuse them too.