ca.criticalpathpartners/primavera-p6-forensic-scheduling
Critical Path Partners
Is the Critical Path Partners MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-14.
Primavera P6 XER forensic scheduling: AACE windows, TIA, impacted as-planned, DCMA-14, Monte Carlo.
alive probed 2026-11-15 · unchanged since 2026-11-14 · HTTP 200
- Endpoint
- https://mcp.criticalpathpartners.ca/mcp (streamable-http)
- Host
- mcp.criticalpathpartners.ca
- Protocol
- 2025-11-25
- Reports itself as
- cpp-forensic-mcp 2.10.17
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- 767 characters
- Of a 1M window
- 2.6 % of a 1M context window
- Count
- 26k tokens in Claude Opus 5.5, exact, measured 2026-11-10. With the Claude Code prefix mcp__…__ on each tool name: 26k. The o200k_base estimate is 16k. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/danafitkowski/cpp-cpm-engine
- Website
- https://criticalpathpartners.ca
- Registry
- active, updated 2026-11-10 · registry entry
- Changes
- 2 recorded, reachable in 2 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.66×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| dcma14_health_check | 4 215 | 2 545 | 16 % |
| impacted_as_planned | 3 607 | 2 178 | 14 % |
| time_impact_analysis_fragnet | 2 501 | 1 510 | 10 % |
| slip_velocity | 2 128 | 1 285 | 8 % |
| concurrent_delay_matrix | 1 953 | 1 179 | 7 % |
Compare this server with others, or with the servers that share its tool set.
Same tool set as 1 other server
These registry entries have the same tool names and the same schema sizes.
- io.github.danafitkowski/cpp-cpm-engine mcp.criticalpathpartners.ca
More servers
Other registry entries on mcp.criticalpathpartners.ca.
- Critical Path Partners io.github.danafitkowski/cpp-cpm-engine · alive
Servers that mention scheduling.
- BAMF.ai ai.bamf/bamf · not MCP
- Chronary ai.chronary/mcp · alive
- RadiusOS CRM ai.radiusos.www/crm · needs auth
- app.reassign/reassign · needs auth
- Schedii app.schedii/mcp · needs auth
- Zooza MCP Server app.zooza/mcp-server · not MCP
- Meet.bot MCP bot.meet/mcp · alive
- eResource Scheduler cloud.eresourcescheduler.app/eresource-scheduler · needs auth
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-10 11:20 | alive | 1.4 s | 14 | 26k | 16k |
| 2026-11-09 11:41 | alive | 1.3 s | 14 | 26k | 16k |
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
- This server is in the heaviest 10 % of the registry. Its 5 most expensive tools are 55 % of the cost. Shorter descriptions, fewer optional parameters and fewer tools cut the cost. The command npx mcpcost --url <endpoint> --tools 50 lists every tool with its cost.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.