46 tools from the Agent Team MCP Server, categorised by risk level.
View the Agent Team policy →ask_user_question Log a question for the user. The orchestrating skill will surface it after dispatch. Include context about why this question matters or what is blo... get_agent_prompt Returns the prompt file for a specific agent role. Use this to load agent identity prompts before spawning specialists. Valid roles: project-manage... get_artifact Get a shared artifact by ID get_decision Get a decision by ID get_discussion Get a discussion including its participants and messages get_my_work Get work entries for a team member, optionally filtered by task get_orchestration_instructions Returns step-by-step instructions for how to orchestrate an AgentTeam. Call this FIRST when a user asks to spin up a team, build something with the... get_project Get a project by ID get_project_summary Get the latest summary for a project get_summary_version Get a specific summary version by its ID get_task Get a task by ID get_team_protocol Returns the shared team protocol, constraints, and efficiency rules that all specialist agents must follow. Call this once on startup. get_work_history Get all work entries for a member within a project list_artifacts List shared artifacts in a project, optionally filtered by type list_decisions List all decisions for a project list_discussions List discussions in a project, optionally filtered by participant list_expansion_requests List team expansion requests for a project, optionally filtered by status (pending, approved, denied) list_journal_entries List journal entries in chronological order. Optionally filter by project_id; omit to list all entries across all projects. 2/5 list_my_comments List all comments made by a member within a project list_projects List all projects, optionally filtered by status list_summary_history List all summary versions for a project list_task_comments List all comments on a task list_tasks List tasks for a project, optionally filtered by assignee or status list_team_members List team members for a project, optionally including removed members list_user_questions List questions logged by specialists for the user. Filter by status (pending, answered) to find unanswered questions. log_decision Log a decision made within a project log_journal_entry Log a user-facing journal entry — captures decisions, preferences, and reasoning from conversations that would otherwise be lost. project_id is opt... log_work Log a work entry for a task by a team member request_team_expansion Request additional team members when your assigned work grows beyond expected scope. The PM will evaluate and approve or deny. share_artifact Share an artifact (document, code, etc.) within a project. Research artifacts must use structured JSON: { "summary": "one sentence", "findings": [{... add_discussion_message Post a message to a discussion (participant must already be in the discussion) 2/5 add_discussion_participant Add a participant to an existing discussion 2/5 add_task_comment Add a comment to a task 2/5 add_team_member Add a team member to a project with a role 2/5 answer_user_question Write the user's answer to a previously asked question 2/5 create_discussion Create a new discussion thread in a project 2/5 create_project Create a new project with a name and description 2/5 create_task Create a new task in a project 2/5 resolve_expansion_request Approve or deny a team expansion request (PM only) 2/5 update_artifact Update the content or title of a shared artifact 2/5 update_discussion_summary Update the summary of a discussion 2/5 update_project_status Update the status of a project (active → paused → completed or archived) 2/5 update_project_summary Create a new versioned summary for a project 2/5 update_task Update a task's status, description, or assignee 2/5 The Agent Team MCP server exposes 46 tools across 3 categories: Read, Write, Destructive.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Agent Team server.
Agent Team tools are categorised as Read (30), Write (14), Destructive (2). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept