com.blackswancausallabs/target-mcp
TARGET Checklist MCP
Score how completely a target-trial-emulation study reports what the TARGET guideline requires.
alive probed 2026-10-15
11tools
6.0ktokens in Claude Opus 5.5
6.1ktokens in Claude Code
3.0 %of a 200k context window
3.6ko200k_base estimate
3.4 sto initialize
8 msto list tools
- Run it
- uvx target-mcp==0.2.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- target-checklist 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- 1 593 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/Black-Swan-Causal-Labs/target-mcp
- Registry
- active, updated 2026-08-23 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| parse_manuscript | 737 | 20 % |
| submit_scaffold_verdicts | 574 | 16 % |
| render_checklist_docx | 423 | 12 % |
| assess_manuscript | 354 | 10 % |
| parse_pmcid | 307 | 9 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/com.blackswancausallabs/target-mcp)
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.