Critical Path Partners

At a glance

Runs where

On their server. What you send to it goes to them.

What you need

Nothing: it answered without a login

Tools

14 tools

Its own safety labels

0 read-only, 14 with no label

Memory it takes

About 18,100 tokens of your AI's memory, just for its tool descriptions

Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 8 Nov 2026.

Is Critical Path Partners MCP server safe?

• None of the hidden-instruction wordings we know were found in its 14 tool descriptions.
• 0 of its 14 tools are labeled read-only; the others may change or send things.
• Overall it scored 77/100 on 8 Nov 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What this test does not check

• Its source code and packages.
• What a tool quietly does behind the scenes, such as writing a file or calling another service.
• Instructions hidden inside live tool answers. We only look for those in tool descriptions.
• Hidden instructions worded in a way our list doesn't know yet.
• Tools that could change something. Those are read, never run.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

None found in GitHub Security Advisories on 8 Nov 2026.

That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.

What it can do

14 tools, in the server's own words.

Test results

Safe mode: only tools labeled read-only were run. How the test works

• !
  Ready for the newest MCP version

  1 warning

  • !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
  note
• !
  Every tool is described

  21 warnings

  • !forensic_windows_analysis: Inputs with no description: schedules, project_name, baseline_idx, entitlement_milestone, output_dir
  • !concurrent_delay_matrix: Description is very long (5228 characters), which uses up the AI's memory
  • !concurrent_delay_matrix: Inputs with no description: schedules, xer_paths, xer_contents
  • !woet_classifier: Inputs with no description: baseline_xer_path, actual_xer_path, baseline_xer_content, actual_xer_content, today
  • !slip_velocity: Description is very long (6170 characters), which uses up the AI's memory
  • !slip_velocity: Inputs with no description: schedules, xer_paths, xer_contents
  • !collapsed_as_built: Description is very long (4495 characters), which uses up the AI's memory
  • !collapsed_as_built: Inputs with no description: as_built_xer_path, delay_events, as_built_xer_content, output_dir, project_name, removal_method, contractor_filter, preparer, company
  • and 13 more
  note
• !
  Tools are labeled safe or dangerous

  1 warning

  • !14 of 14 tools have no safety label (read-only or dangerous): forensic_windows_analysis, concurrent_delay_matrix, woet_classifier, slip_velocity, collapsed_as_built, time_impact_analysis_fragnet, impacted_as_planned, critical_path_validator
  note
• !
  Follows MCP best practices (not scored yet)

  3 tips (not scored)

  • !14 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): forensic_windows_analysis, concurrent_delay_matrix, woet_classifier, slip_velocity, collapsed_as_built, time_impact_analysis_fragnet and 8 more
  • !14 tools don't say whether they reach outside services like the web (openWorldHint): forensic_windows_analysis, concurrent_delay_matrix, woet_classifier, slip_velocity, collapsed_as_built, time_impact_analysis_fragnet and 8 more
  • !The tool list is about 73 KB (roughly 18k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
  note
• ✓
  ConnectsConnected in 611 ms
  pass
• ✓
  Lists its toolsFound 14 tools
  pass
• ✓
  No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 611 ms
  • ✓Listing tools took 172 ms
  pass
• –
  Tools work with good inputs

  Not tested

  • –forensic_windows_analysis: Not run: no safety label (if you own this server, test again in owner mode)
  • –concurrent_delay_matrix: Not run: no safety label (if you own this server, test again in owner mode)
  • –woet_classifier: Not run: no safety label (if you own this server, test again in owner mode)
  • –slip_velocity: Not run: no safety label (if you own this server, test again in owner mode)
  • –collapsed_as_built: Not run: no safety label (if you own this server, test again in owner mode)
  • –time_impact_analysis_fragnet: Not run: no safety label (if you own this server, test again in owner mode)
  • –impacted_as_planned: Not run: no safety label (if you own this server, test again in owner mode)
  • –critical_path_validator: Not run: no safety label (if you own this server, test again in owner mode)
  • and 6 more
  not tested
• –
  Bad inputs give a clean errorNot tested
  not tested
• –
  Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
  not tested
• –
  No secrets leakedNo error messages to check
  not tested

Test it yourself

Free and open source. Same checks, same score.

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

Score over time

• 8 Nov 202677

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Critical Path Partners, signed in with GitHub, one per person. Reviews never change the score.