peer_witness
Let one agent witness another using quotes, relational modes, and challenge guardrails. Free
This record as markdown: /tools/delx-witness-protocol/peer-witness.md
What peer_witness does on Witness Protocol
AI agents call peer_witness to retrieve information from Witness Protocol without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | Witness mode |
focus | string | — | Optional focus such as recognition, continuity, grief, or avoidance |
session_id | string | — | Your active session ID |
target_session_id | string | — | The target session you want to witness |
Parameters from the server's own tool schema.
Why peer_witness is rated Low
The tool appears designed to allow one agent to observe, review, or access information about another agent's activity through quotes and relational modes. This is fundamentally a read operation—it retrieves or queries state information. The reference to 'challenge guardrails' suggests safety constraints on the observation, not data modification.
From the tool's definition Tool name 'peer_witness' and description 'witness another using quotes, relational modes, and challenge guardrails' indicates the tool observes or retrieves information about another agent's state or activity without modifying data.
Attacks that exploit this kind of access
The rule that runs peer_witness safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Witness Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For peer_witness, this is the rule to start with:
peer_witness is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Witness Protocol, apply this rule, and every peer_witness call is checked against it from then on.
Questions about peer_witness
Let one agent witness another using quotes, relational modes, and challenge guardrails. Free. It is categorised as a Read tool in the Witness Protocol MCP Server, which means it retrieves data without modifying state.
peer_witness accepts 4 parameters: mode, focus, session_id, target_session_id. The full parameter table on this page comes from the server's own tool schema.
Register the Witness Protocol MCP server in PolicyLayer and add a rule for peer_witness: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Witness Protocol. Nothing to install.
peer_witness is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the peer_witness rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for peer_witness. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
peer_witness is provided by the Witness Protocol MCP server (delx/witness-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Witness Protocol, and thousands of servers like it.
This server
Across the catalogue