Compute the C-axis fractional weight vector from a list of inference billing records (prompt_tokens, completion_tokens). Returns canonical ComputeAxisEntry[] with 6-digit decimal compute_share strings that sum to ~1.0 and feed directly into aps_construct_attribution_primitive. Weights = prompt_to...
AI agents call aps_compute_compute_axis_weights to retrieve information from Agent Passport System — Cryptographic Identity for AI Agents without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
profile | object | — | Optional WeightProfile override; defaults to DEFAULT_WEIGHT_PROFILE |
providers | array | Yes | Per-provider billing records |
Parameters from the server's own tool schema.
This tool performs a pure computation/calculation — it takes billing records (token counts) as input and returns normalized weight vectors. There are no side effects described: no data is written, no commands are executed, no money is moved. It feeds results into another tool but does not itself perform any mutation.
From the tool's definition 'Compute the C-axis fractional weight vector from a list of inference billing records' and 'Returns canonical ComputeAxisEntry[] with 6-digit decimal compute_share strings that sum to ~1.0'
Documented attack patterns abuse exactly the kind of access aps_compute_compute_axis_weights gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Passport System — Cryptographic Identity for AI Agents, and nothing reaches the server without passing your rules. This is the rule we recommend for aps_compute_compute_axis_weights:
{
"version": "1",
"default": "deny",
"tools": {
"aps_compute_compute_axis_weights": {}
}
}aps_compute_compute_axis_weights is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
All 150 Agent Passport System — Cryptographic Identity for AI Agents tools →
Compute the C-axis fractional weight vector from a list of inference billing records (prompt_tokens, completion_tokens). Returns canonical ComputeAxisEntry[] with 6-digit decimal compute_share strings that sum to ~1.0 and feed directly into aps_construct_attribution_primitive. Weights = prompt_tokens + completion_tokens × COMPLETION_MULTIPLIER (default 3.0), normalized per spec BUILD-B §'The C-axis formula'. Parameter names match the SDK: providers, optional profile. It is categorised as a Read tool in the Agent Passport System — Cryptographic Identity for AI Agents MCP Server, which means it retrieves data without modifying state.
aps_compute_compute_axis_weights accepts 2 parameters: profile, providers. Required: providers. The full parameter table on this page comes from the server's own tool schema.
Register the Agent Passport System — Cryptographic Identity for AI Agents MCP server in PolicyLayer and add a rule for aps_compute_compute_axis_weights: 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 Agent Passport System — Cryptographic Identity for AI Agents. Nothing to install.
aps_compute_compute_axis_weights 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 aps_compute_compute_axis_weights 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 aps_compute_compute_axis_weights. 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.
aps_compute_compute_axis_weights is provided by the Agent Passport System — Cryptographic Identity for AI Agents MCP server (https://mcp.aeoess.com/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Passport System — Cryptographic Identity for AI Agents, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
150 Agent Passport System — Cryptographic Identity for AI Agents tools catalogued and risk-classified — across an index of 43,000+ MCP servers.