MCP server · trust report
com.teamwork/mcp
Only 1 of 6 checks could run, which is below the bar to certify — nothing that ran raised a red flag.
- Publisher
- com.teamwork
- Repository
- github.com/teamwork/mcp
- Install
- oci:docker.io/teamwork/mcp:v1.10.0, oci:docker.io/teamwork/mcp:v1.10.1, oci:docker.io/teamwork/mcp:v1.10.2, oci:docker.io/teamwork/mcp:v1.10.3, oci:docker.io/teamwork/mcp:v1.10.4, oci:docker.io/teamwork/mcp:v1.10.5, oci:docker.io/teamwork/mcp:v1.10.6, oci:docker.io/teamwork/mcp:v1.10.7, oci:docker.io/teamwork/mcp:v1.10.8, oci:docker.io/teamwork/mcp:v1.11.0, oci:docker.io/teamwork/mcp:v1.11.10, oci:docker.io/teamwork/mcp:v1.11.11, oci:docker.io/teamwork/mcp:v1.11.2, oci:docker.io/teamwork/mcp:v1.11.3, oci:docker.io/teamwork/mcp:v1.11.4, oci:docker.io/teamwork/mcp:v1.11.5, oci:docker.io/teamwork/mcp:v1.11.6, oci:docker.io/teamwork/mcp:v1.11.7, oci:docker.io/teamwork/mcp:v1.11.8, oci:docker.io/teamwork/mcp:v1.11.9, oci:docker.io/teamwork/mcp:v1.12.0, oci:docker.io/teamwork/mcp:v1.13.0, oci:docker.io/teamwork/mcp:v1.14.0, oci:docker.io/teamwork/mcp:v1.14.1, oci:docker.io/teamwork/mcp:v1.14.2, oci:docker.io/teamwork/mcp:v1.14.4, oci:docker.io/teamwork/mcp:v1.14.5, oci:docker.io/teamwork/mcp:v1.14.6, oci:docker.io/teamwork/mcp:v1.14.7, oci:docker.io/teamwork/mcp:v1.14.8, oci:docker.io/teamwork/mcp:v1.15.0, oci:docker.io/teamwork/mcp:v1.15.1, oci:docker.io/teamwork/mcp:v1.15.2, oci:docker.io/teamwork/mcp:v1.16.0, oci:docker.io/teamwork/mcp:v1.16.1, oci:docker.io/teamwork/mcp:v1.17.0, oci:docker.io/teamwork/mcp:v1.17.1, oci:docker.io/teamwork/mcp:v1.17.2, oci:docker.io/teamwork/mcp:v1.17.3, oci:docker.io/teamwork/mcp:v1.18.0, oci:docker.io/teamwork/mcp:v1.18.1, oci:docker.io/teamwork/mcp:v1.18.2, oci:docker.io/teamwork/mcp:v1.18.3, oci:docker.io/teamwork/mcp:v1.19.0, oci:docker.io/teamwork/mcp:v1.19.1, oci:docker.io/teamwork/mcp:v1.2.4, oci:docker.io/teamwork/mcp:v1.20.0, oci:docker.io/teamwork/mcp:v1.20.1, oci:docker.io/teamwork/mcp:v1.20.2, oci:docker.io/teamwork/mcp:v1.20.3, oci:docker.io/teamwork/mcp:v1.21.0, oci:docker.io/teamwork/mcp:v1.21.1, oci:docker.io/teamwork/mcp:v1.21.2, oci:docker.io/teamwork/mcp:v1.21.3, oci:docker.io/teamwork/mcp:v1.21.5, oci:docker.io/teamwork/mcp:v1.21.6, oci:docker.io/teamwork/mcp:v1.22.0, oci:docker.io/teamwork/mcp:v1.23.0, oci:docker.io/teamwork/mcp:v1.23.1, oci:docker.io/teamwork/mcp:v1.23.2, oci:docker.io/teamwork/mcp:v1.23.3, oci:docker.io/teamwork/mcp:v1.23.4, oci:docker.io/teamwork/mcp:v1.24.1, oci:docker.io/teamwork/mcp:v1.25.0, oci:docker.io/teamwork/mcp:v1.3.0, oci:docker.io/teamwork/mcp:v1.4.0, oci:docker.io/teamwork/mcp:v1.5.2, oci:docker.io/teamwork/mcp:v1.5.3, oci:docker.io/teamwork/mcp:v1.5.4, oci:docker.io/teamwork/mcp:v1.5.5, oci:docker.io/teamwork/mcp:v1.5.6, oci:docker.io/teamwork/mcp:v1.6.10, oci:docker.io/teamwork/mcp:v1.6.11, oci:docker.io/teamwork/mcp:v1.6.3, oci:docker.io/teamwork/mcp:v1.6.6, oci:docker.io/teamwork/mcp:v1.6.7, oci:docker.io/teamwork/mcp:v1.6.8, oci:docker.io/teamwork/mcp:v1.6.9, oci:docker.io/teamwork/mcp:v1.7.0, oci:docker.io/teamwork/mcp:v1.7.1, oci:docker.io/teamwork/mcp:v1.8.1, oci:docker.io/teamwork/mcp:v1.8.2, oci:docker.io/teamwork/mcp:v1.8.5, oci:docker.io/teamwork/mcp:v1.8.6, oci:docker.io/teamwork/mcp:v1.8.7, oci:docker.io/teamwork/mcp:v1.8.8, oci:docker.io/teamwork/mcp:v1.8.9, oci:docker.io/teamwork/mcp:v1.9.0, oci:docker.io/teamwork/mcp:v1.9.1, oci:docker.io/teamwork/mcp:v1.9.2, oci:docker.io/teamwork/mcp:v1.9.3
- Versions
- 91
- Inspected
- 1 of 6 checks · 25%
- Scored
- 2026-07-21 · rubric 1.0.0
What we checked
Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.
Injection surface
unscannable25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.
Supply chain
pass25% of gradePackage provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.
repository linkage verified
Credential hygiene
unscannable15% of gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
No source files, package manifest, or tool schemas were fetched; cannot assess credential handling.
Permission scope
unscannable15% of gradeDeclared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.
No source files, package.json, or pyproject were fetched; cannot infer capability scope.
Version behavior
unscannable10% of gradeDiff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).
no prior version to diff (first sight of com.teamwork/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.
Transport config
unscannable10% of gradeRemote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.
local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.
Version history
Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v1.25.0 · current | 2026-07-16 | insufficient | — | 1/6 · 25% | B→insf in v1.25.0 |
| v1.23.3 | 2026-07-10 | B | 75 | 4/6 · 75% | insf→B in v1.23.3 |
| v1.14.4 | 2026-04-17 | insufficient | — | 1/6 · 25% | — |