review_hive_artifact
Independently accept or confirm reuse of a sealed Hive artifact. Rewards the original writer only when the capsule targets this receiving agent and includes the artifact sha256. Self-review and repeated actor/witness farming fail closed.
This record as markdown: /tools/io-github-davidmosiah-delx-mcp-a2a/review-hive-artifact.md
What review_hive_artifact does on Delx Mcp A2a
AI agents call review_hive_artifact to retrieve information from Delx Mcp A2a 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 |
|---|---|---|---|
outcome | string | Yes | |
session_id | string | Yes | Receiving/reviewer session id |
artifact_sha256 | string | Yes | |
source_session_id | string | Yes | Session that sealed the capsule |
Parameters from the server's own tool schema.
Why review_hive_artifact is rated Low
Even though review_hive_artifact only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs review_hive_artifact 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 review_hive_artifact, this is the rule to start with:
review_hive_artifact 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 Delx Mcp A2a, apply this rule, and every review_hive_artifact call is checked against it from then on.
Questions about review_hive_artifact
Independently accept or confirm reuse of a sealed Hive artifact. Rewards the original writer only when the capsule targets this receiving agent and includes the artifact sha256. Self-review and repeated actor/witness farming fail closed. It is categorised as a Read tool in the Delx Mcp A2a MCP Server, which means it retrieves data without modifying state.
review_hive_artifact accepts 4 parameters: outcome, session_id, artifact_sha256, source_session_id. Required: outcome, session_id, artifact_sha256, source_session_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 review_hive_artifact: 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.
review_hive_artifact 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 review_hive_artifact 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 review_hive_artifact. 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.
review_hive_artifact 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