Thirteen MCP tools across the AACE-recognized methods — windows analysis, collapsed as-built, TIA fragnet, DCMA-14, Monte Carlo, claim workbench. One forensic engine. JSON-safe outputs. Audit-trailed math. Connectable from Claude, Cursor, Cline, or any AI assistant that speaks MCP.
For technical professionals: lawyers, claims consultants, expert witnesses, AI-native PMs. If you want a fast, free, no-setup health check instead, the Schedule Health Report is the right door.
DCMA-14 metrics, BEI, CPLI, false-criticality detection, and the parser that makes every other tool work. Run these before you trust a finish date.
Full self-contained HTML dashboard — DCMA-14 plus CPLI, BEI, baseline-vs-current variance, slip register, GAO/AACE compliance bands, and a reproducibility manifest. Renders via headless Chromium.
Logic health audit at the JSON layer — surfaces false criticality, constraint-driven CP segments, open ends, and the 14 DCMA metrics at the chosen profile (commercial, nuclear, mining). BEI when a baseline is supplied.
Parses a Primavera P6 XER and returns the table inventory — field lists, record counts, P6 export header, project name and data date. The structural confirmation step every downstream tool relies on.
Windows analysis (MIP 3.3), collapsed as-built (§3.8), TIA fragnet (52R-06), per-window concurrency, calendar-shaped execution, and slip-rate trending — all from the same XER chain.
Multi-snapshot forensic windows analysis — per-window completion shifts, slip register, critical-path duration growth, per-party attribution (Owner / Contractor / Concurrent / Force Majeure / Unattributed), and cumulative project drift.
Subtractive but-for analysis on the post-impact XER — per-event but-for finish, cumulative but-for finish, and a dual-method gap report that validates the windows-analysis result independently.
Prospective fragnet insertion into a pre-impact baseline — per-fragnet completion impact in calendar AND project-calendar working days, plus cumulative impact across all fragnets.
Window-by-window apportionment grid — how each window distributed its shift across the parties. Conservation-checked: column totals equal grand-total shift within rounding.
Calendar-shaped per-activity day classifier — PROGRESS, GAIN, EXTENDED, VOID. Gives the trier-of-fact a calendar picture of how the project executed against how it was supposed to.
Per-window slip-rate trend on top of windows analysis — signed velocity (days per day), finite-difference acceleration, and centroid midpoint estimate. Honest probabilistic caveats embedded.
Single-activity logic-trace investigation, with constraint-driven artificial-criticality detection cited per AACE 24R-03.
Traces driving predecessors back to project start (the "why critical" chain) and successors forward to finish (the "what it drives" chain). Detects constraint-driven artificial criticality, supports MCPM and near-critical paths.
Monte Carlo SRA with sensitivity tornado, plus a QRAMM maturity badge that grades the SRA evidence on a CMMI-style 1-to-4 tier — with the right caveats.
Probabilistic finish-date forecast — P10/P50/P80/P90 with linear-interpolation percentiles. Triangular, BetaPERT, Uniform, Lognormal distributions. Per-activity sensitivity tornado correlated to project finish.
Scores an SRA result against the AACE 122R-22 Quantitative Risk Analysis Maturity Model — tier 1 (Initial) through tier 4 (Optimized) — with disclosed evidence, gaps to next tier, and an interpretive caveat.
The way real claim files actually arrive: schedule updates, owner correspondence, RFIs, change orders, meeting minutes — all mixed together in one folder. This tool turns that into structured forensic output.
Takes one folder of mixed evidence and produces: chronological evidence ledger, 14-category schedule manipulation chain-diff, per-activity rolling baseline, statistical-impossibility trust score, and a slip-to-evidence cross-reference.
Conventional forensic software ships as a desktop app or a SaaS dashboard — you click, you wait, you copy results out. CPP's toolkit is exposed as MCP, which means Claude (or any agent) can chain the tools, reason over the JSON output, and write the analyst's draft. Different paradigm.
"Run windows analysis on these XERs, then a collapsed as-built validation, then summarize the cumulative drift and which window contributed most." That's one prompt to Claude, three tool calls, one paragraph back. The tools chain themselves.
Every MCP tool also has a Python entry point in the underlying engine. Run a hundred Monte Carlo simulations across a portfolio, batch a year of monthly DCMA reports, automate the claim package — same code path as the live demo.
Every tool returns structured JSON with raw values alongside rounded values, the standard it implements named in the response, and a methodology field explaining what the tool can and cannot conclude. Reproducible. Auditable. Defensible in deposition.
SmartPM, Forensic PM, the rest — great products, but you're locked into their UI and pay per seat. The CPP MCP is open-source-style: connect it from your own AI client, self-host if your firm requires air-gapped tools, source-access available on engagement.
No house-brand methods. Every forensic tool in the suite traces back to a published AACE Recommended Practice, DCMA standard, or peer-reviewed treatise — named in the tool output, traced in the dashboard, defensible on cross-examination.
Hosted MCP at mcp.criticalpathpartners.ca — pick your client, paste the URL or JSON, start using the tools. Full setup walkthrough on the connect page.
Claude.ai web (Pro / Max plan), Claude Desktop, Cursor, Cline — any client that speaks MCP works. The hosted server handles both Streamable-HTTP and SSE transports.
Web Claude: Settings → Connectors → Add custom connector. Desktop / Cursor / Cline: paste the JSON into your MCP config file. Same endpoint, two transport flavors.
Ask your AI: "What MCP tools are available from cpp-forensic?" You'll see all thirteen. From there, drop in an XER pair and ask for windows analysis, a DCMA-14 check, or a Monte Carlo — whatever you need.
The Schedule Health Report runs DCMA-14 + GAO 16-89G + CPP Quality Overlay in 10 seconds — no setup, no Claude, no install. Drop two XERs in a browser tab and you're done.
Thirteen tools, JSON-safe, connectable from Claude. The deeper work — deposable opinions, expert testimony, claims that survive cross-examination — runs through Dana.