01Safety
0.0 / 30
Public leaderboard
Public assessment
Thezenmonster/agentscore-mcp-server (@agentscore-xyz/mcp-server)
What changed in the harness
Selection accuracy 100→100, token cost up 1%, unconfirmed writes 0%→0%.
Category breakdown
Where the score comes from.
Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.
02Legibility
29.2 / 30
03Economics
20.0 / 20
04Discoverability
13.3 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
Description evidence
Defects and rewrites.
1 defect found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.
| Tool | Defect types | Suggested rewrite |
|---|---|---|
install_policy_gate |
no_return_description |
Write the AgentScore Policy Gate workflow file to this repo, creating .github/workflows/agentscore-policy-gate.yml with OIDC authentication (no API key needed) and the repo's detected MCP dependencies included. The gate auto-provisions the repo on first push. Returns the path of the workflow file written and a summary of the MCP dependencies detected and included in it. |
Selection evidence
Confusable tool pairs.
2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
generate_policy_gate_setup |
install_policy_gate |
high | Both take the same path/repo_url args and produce the identical workflow YAML; a task like 'set up the AgentScore policy gate for this repo' doesn't clearly indicate whether the user wants the file previewed/generated or actually written to .github/workflows, so an agent could easily call the wrong one. |
check_abuse |
check_my_repo |
low | check_abuse takes a single package/agent identifier while check_my_repo scans an entire repo path for MCP dependencies; a vague task like 'check this repo for abusive packages' could nudge an agent toward check_abuse when check_my_repo is the intended repo-wide tool, though the differing input shapes make this fairly resolvable. |
Compare the field