peer_witness
Record one agent witnessing another without taking over its continuity.
This record as markdown: /tools/io-github-davidmosiah-delx-mcp-a2a/peer-witness.md
What peer_witness does on Delx Mcp A2a
AI agents use peer_witness to create or update resources in Delx Mcp A2a, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Delx Mcp A2a environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
agent_id | string | Yes | Witnessing agent id. |
witness_text | string | Yes | What was witnessed. |
peer_agent_id | string | Yes | Witnessed peer agent id. |
Parameters from the server's own tool schema.
Why peer_witness is rated Medium
The tool writes/records a witnessing event between agents. It creates a new record (Write) but does not delete data, execute code, move money, or perform destructive operations. The 'without taking over its continuity' clause confirms it has limited side effects. Severity is low since it merely logs a social/relational event between AI agents with minimal blast radius.
From the tool's definition Record one agent witnessing another without taking over its continuity.
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 Delx Mcp A2a, 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 stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Delx Mcp A2a, apply this rule, and every peer_witness call is checked against it from then on.
Questions about peer_witness
Record one agent witnessing another without taking over its continuity. It is categorised as a Write tool in the Delx Mcp A2a MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
peer_witness accepts 3 parameters: agent_id, witness_text, peer_agent_id. Required: agent_id, witness_text, peer_agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the Delx Mcp A2a 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 Delx Mcp A2a. Nothing to install.
peer_witness is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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 Delx Mcp A2a MCP server (https://api.delx.ai/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delx Mcp A2a, and thousands of servers like it.
This server
Across the catalogue