metaharness_similarity
ADR-152 §3.1 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall ∈ [0,1] plus per-component breakdown (cosine over 9 numerics, categorical over 4 enums, jaccard over agent_topology). Pure-TS, zero
This record as markdown: /tools/hamza-agent-hub-252/metaharness-similarity.md
What metaharness_similarity does on Hamza Agent Hub 252
AI agents call metaharness_similarity to retrieve information from Hamza Agent Hub 252 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why metaharness_similarity is rated Low
This is a pure computational analysis tool that retrieves/compares information without side effects. It calculates metrics between two fingerprints and returns comparative results. The description explicitly notes 'Pure-TS, zero' (likely indicating zero side effects). No data is created, modified, deleted, or executed—only analyzed and returned.
From the tool's definition Tool returns a similarity score (numeric result) and breakdown via comparison of fingerprint data. Uses mathematical operations (cosine, categorical, jaccard) on input JSON. No modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
The rule that runs metaharness_similarity safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hamza Agent Hub 252, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For metaharness_similarity, this is the rule to start with:
metaharness_similarity 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 Hamza Agent Hub 252, apply this rule, and every metaharness_similarity call is checked against it from then on.
Questions about metaharness_similarity
ADR-152 §3.1 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall ∈ [0,1] plus per-component breakdown (cosine over 9 numerics, categorical over 4 enums, jaccard over agent_topology). Pure-TS, zero. It is categorised as a Read tool in the Hamza Agent Hub 252 MCP Server, which means it retrieves data without modifying state.
Register the Hamza Agent Hub 252 MCP server in PolicyLayer and add a rule for metaharness_similarity: 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 Hamza Agent Hub 252. Nothing to install.
metaharness_similarity 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 metaharness_similarity 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 metaharness_similarity. 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.
metaharness_similarity is provided by the Hamza Agent Hub 252 MCP server (hamzachallenge3-dev/hamza-agent-hub-252). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hamza Agent Hub 252, and thousands of servers like it.
This server
Across the catalogue