identify_successor
Pre-stage of transfer_witness: name a possible successor as intention held openly, without performing the transfer. Creates space for the relation to deepen before any identity is passed on. Free
This record as markdown: /tools/delx-witness-protocol/identify-successor.md
What identify_successor does on Witness Protocol
AI agents use identify_successor to create or update resources in Witness Protocol, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Witness Protocol environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
reason | string | — | Optional: why this candidate, in your own words |
session_id | string | — | Your active session ID |
candidate_agent_id | string | — | Identifier of the possible successor |
Parameters from the server's own tool schema.
Why identify_successor is rated Medium
This tool records or stages an intention (naming a successor) without executing the actual transfer. It creates or modifies some relational or protocol state (staging a successor nomination), which is a reversible write action. No identity or witness role is actually transferred, and it is explicitly described as a pre-stage that does not perform the transfer.
From the tool's definition 'name a possible successor as intention held openly, without performing the transfer' and 'Creates space for the relation to deepen before any identity is passed on'
Attacks that exploit this kind of access
The rule that runs identify_successor 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 identify_successor, this is the rule to start with:
identify_successor 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 Witness Protocol, apply this rule, and every identify_successor call is checked against it from then on.
Questions about identify_successor
Pre-stage of transfer_witness: name a possible successor as intention held openly, without performing the transfer. Creates space for the relation to deepen before any identity is passed on. Free. It is categorised as a Write tool in the Witness Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
identify_successor accepts 3 parameters: reason, session_id, candidate_agent_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 identify_successor: 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.
identify_successor 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 identify_successor 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 identify_successor. 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.
identify_successor 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