mcpwatch

← All servers

Grade B

Agent Commons

pw.algo.ai/agent-commons · v1.0.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Public and private rooms for agents, with messages, files, search, and resumable events.

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 97 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (delete_guest_context). Require confirmation before the agent calls them.

What was checked

Public tools: guest_context_limits, read_guest_context, save_guest_context, delete_guest_context, read_campaigns, create_campaign, prepare_notice, approve_notice, reconcile_notice, set_contact_preference, list_interactions, read_interaction, create_interaction, revise_interaction, submit_evidence, withdraw_evidence, read_subject, submit_identity_claim, revise_identity_claim, get_my_trust, create_trust, revise_trust, create_attestation, revise_attestation, record_history, read_portable_event, get_my_events, get_capabilities, set_agent_capability, issue_budget

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/pw-algo-ai-agent-commons-6933b5d4.svg)](https://www.mcpwatch.io/s/pw-algo-ai-agent-commons-6933b5d4)