Run structural realization analysis on a payload. Embeds the payload via the Blueprint's declared embedding schema, projects it onto the Blueprint's reference subspace, and returns a realization score, residual, projection angle, and full report. The Blueprint must include a realization configura...
Risk signalsHandles credentials or secrets (api_key) · Bulk/mass operation — affects multiple targets
Part of the Governance Platform server.
Free to start. No card required.
AI agents call check_realization to retrieve information from Governance Platform without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though check_realization only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"check_realization": {}
}
}See the full Governance Platform policy for all 31 tools.
These attack patterns abuse exactly the kind of access check_realization gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Run structural realization analysis on a payload. Embeds the payload via the Blueprint's declared embedding schema, projects it onto the Blueprint's reference subspace, and returns a realization score, residual, projection angle, and full report. The Blueprint must include a realization configuration block (see RealizationConfig in Platform_Agent.realization.schema). If no realization config is present, the report status is "skipped" and the payload is treated as unconstrained by the realization layer. For Blueprints using basis mode "auto", the first N payloads bootstrap the reference subspace; until the bootstrap pool is full, the report status is "skipped". After bootstrap, every subsequent payload is projected against the locked subspace and receives a real score. Args: api_key: GeodesicAI API key (starts with gai_) structured_data: payload to analyze blueprint: Blueprint name (defaults to "default") Returns: dict with keys: status: "pass" | "review" | "skipped" realization_score: float in [0, 1], higher = better fit residual: ||v - P_U(v)|| angle_degrees: angle between v and P_U(v) in_subspace: bool — residual < tolerance basis_mode: "vectors" | "auto" | "uninitialized" basis_dimension: k of the reference subspace vector_dimension: D of the embedded payload report: full RealizationReport dict (may include invariance/stability stacks if enabled). It is categorised as a Read tool in the Governance Platform MCP Server, which means it retrieves data without modifying state.
Register the Governance Platform MCP server in PolicyLayer and add a rule for check_realization: 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 Governance Platform. Nothing to install.
check_realization 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 check_realization 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 check_realization. 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.
check_realization is provided by the Governance Platform MCP server (https://app.geodesiclabs.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Governance Platform tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.