ModelsAtlas
Explore
Atlas / MCP servers / dkships / PM Copilot

PM CopilotSAFE

mcp/dkships/pm-copilot
MCP server by dkships · ai tools · claude · customer feedback · Audited 2026-10-08
⚑ Report / re-scanSource ↗

MCP server that triangulates customer support tickets and feature requests to help PMs decide what to build next

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 5r · 0w · 0d
Transport
stdio
License
MIT
Stars
30
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

An MCP server that triangulates customer support tickets, feature requests, and AI support agent conversations to help PMs decide what to build next.

[](#) [](LICENSE) [](#) [](#)

Real results: Analyzed 3,353 signals in one 30-day window: 1,678 support tickets, 276 feature requests, and 1,399 AI support agent conversations across 4 products. The chats are signal a ticket-only analysis never sees.

Read the full story: I built an MCP server that changed how I prioritize products

What makes this different

  • Signal triangulation. Matches support tickets against feature requests to find convergent themes, and gives convergent themes a 2x priority boost.
  • The deflection blind spot. An AI support agent answers questions that never become tickets, so ticket-based prioritization undercounts every theme the bot handles. Chatbase conversations come in as a third signal class, with a per-theme self_serve_failure_rate.
  • Composability. Pass churn or traffic data from other MCP servers into generate_product_plan via kpi_context, and the methodology adjusts priorities.

Architecture

graph TD
A[Claude Desktop / Code] -->|stdio| B[pm-copilot]
A -->|stdio| C[Metabase MCP]
A -->|stdio| D[Google Analytics MCP]
B -->|Reactive| E[HelpScout: tickets]
B -->|Proactive| F[ProductLift: feature requests]
B -->|Deflected| I[Chatbase: AI agent chats]
C -->|Quantitative| G[Conversion, Churn, Revenue]
D -->|Acquisition| H[Traffic, Channels, Trends]
B -.->|kpi_context| A

##

Read from source at commit 6af2ad9faf64OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add pm-copilot --env CHATBASE_API_KEY=${CHATBASE_API_KEY} --env HELPSCOUT_APP_SECRET=${HELPSCOUT_APP_SECRET} --env PRODUCTLIFT_API_KEY=${PRODUCTLIFT_API_KEY} -- npx -y @dkships/[email protected]
claude-desktop
{
  "mcpServers": {
    "pm-copilot": {
      "command": "npx",
      "args": [
        "-y",
        "@dkships/[email protected]"
      ],
      "env": {
        "CHATBASE_API_KEY": "${CHATBASE_API_KEY}",
        "HELPSCOUT_APP_SECRET": "${HELPSCOUT_APP_SECRET}",
        "PRODUCTLIFT_API_KEY": "${PRODUCTLIFT_API_KEY}"
      }
    }
  }
}
03

Exposed tools (5)

5 read · 0 write · 0 destructive.

ToolRiskDescription
generate_product_planread
get_feature_requestsread
get_theme_evidenceread
list_sourcesread
synthesize_feedbackread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (4 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

MEDIUMInventory / provenance · inv.binary · CWE-1104
src/theme-eval.ts
theme-eval.ts
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, dotenv, zod, @types/node, typescript, vitest
Why it matters. 6 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 6af2ad9faf64full audit observations/trust-audit/mcp-server/dkships__pm-copilot.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-086af2ad9faf64SAFEB89first audit
06

Questions

What is the PM Copilot MCP server?

MCP server that triangulates customer support tickets and feature requests to help PMs decide what to build next

What tools does PM Copilot expose?

5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is PM Copilot safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does PM Copilot need?

It reads CHATBASE_API_KEY, HELPSCOUT_APP_SECRET and PRODUCTLIFT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does PM Copilot run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @dkships/pm-copilot at 1.8.0.

How current is this page?

The grade is for one exact copy of the source (6af2ad9faf64), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement