AGENT EVIDENCE MCP TOOLS

16 tools from the Agent Evidence MCP MCP Server, categorised by risk level.

// ALL 16 AGENT EVIDENCE MCP TOOLS

READ 11 tools

Read capture_checkpoint Capture a screenshot checkpoint for a session at an important milestone. Read capture_screenshot Capture a raw screenshot artifact for a session. Read compare_artifacts Compare two artifacts from the same session and return a review-oriented verdict, changed fields, and follo... Read compare_latest_artifacts Compare the two most recent comparable artifacts in a session, optionally filtered by artifact type. Read end_session Mark a session as completed and refresh its summary. Read get_latest_session Return the newest evidence session, optionally filtered by status. Read get_recording_status Report whether a session currently has an active recording. Read get_session Load a session by session id or session directory path. Read list_artifacts List saved artifacts for an existing evidence session. Read list_sessions List evidence sessions, newest first. Optionally filter by status or limit the number returned. Read ocr_artifact Attach OCR text to an existing artifact for review and searchability.

WRITE 2 tools

Write attach_note Attach a human-readable note to an existing artifact. Write redact_artifact Create a new redacted screenshot artifact from an existing screenshot using one or more rectangular regions.

EXECUTE 3 tools

Execute start_recording Start a short recording for an existing session. Execute start_session Create a new evidence session for a long-running task. Execute stop_recording Stop the active recording for a session and save it as an artifact.

// FAQ

How many tools does the Agent Evidence MCP MCP server have? +

The Agent Evidence MCP MCP server exposes 16 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Agent Evidence MCP tools? +

Route the Agent Evidence MCP server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Agent Evidence MCP tools fall into? +

Agent Evidence MCP tools are categorised as Read (11), Write (2), Execute (3). Each category has a recommended default policy.

Enforce policy on every Agent Evidence MCP tool call.

Start from Agent Evidence MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.