MCP Tool Trust, Permission & Schema Drift Intelligence
Pricing
from $11.20 / 1,000 results
MCP Tool Trust, Permission & Schema Drift Intelligence
Use this Actor to monitor mcp tool trust, permission and schema drift changes and return decision-ready change signals. Compare MCP tool snapshots for permission expansion, schema drift and poisoning signals, then emit trust scores and ALLOW, REVIEW or BLOCK actions.
Pricing
from $11.20 / 1,000 results
Rating
0.0
(0)
Developer
Rafael Barreto Haddad
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
4 hours ago
Last modified
Categories
Share
Use this Actor to monitor mcp tool trust, permission and schema drift changes and return decision-ready change signals. It is designed for repeatable human, API, Apify AI, and MCP-driven workflows.
Compare MCP tool snapshots for permission expansion, schema drift and poisoning signals, then emit trust scores and ALLOW, REVIEW or BLOCK actions.
Why use this Actor
Agent teams need continuous evidence when an MCP tool silently changes permissions, arguments, descriptions or destructive behavior after initial approval. This Actor sits above raw extraction: supply a current dataset, optionally add a previous snapshot, and receive an aggregated report built for recurring monitoring and AI-agent workflows.
Key features
-
Combines permission drift, schema drift and tool-description poisoning signals in one baseline model.
-
Focuses on before-versus-after trust changes rather than one-time vulnerability scanning.
-
Emits deterministic ALLOW, REVIEW and BLOCK decisions for agent workflows.
-
Reads inline JSON rows or Apify Dataset IDs with limited READ permission.
-
Writes one auditable report to the default Dataset and
INTELLIGENCE_REPORT.
Input
Provide currentItems directly or select an Apify Dataset with currentDatasetId. For change intelligence, add the prior period with previousItems or previousDatasetId. maxItems caps dataset loading. Optional Gen2 fields can provide a previous analysis and user-supplied economic assumptions.
Output
The Actor writes one decision-ready report to the default Dataset and to INTELLIGENCE_REPORT in the key-value store. The report includes counts, ranked signals, baseline evidence, confidence, regression state, an executive decision, recommended action, and the domain-specific portfolio score.
Example
Use the prefilled example or replace currentItems with rows from an upstream Actor. On recurring runs, provide the prior period in previousItems or previousDatasetId. The Actor normalizes common aliases, compares snapshots, ranks the strongest entity changes and emits agentAction.
Use cases
- MCP governance.
- AI agent security.
- tool allowlist monitoring.
- enterprise agent platforms.
Pricing
One primary pay-per-event outcome: one decision-ready intelligence report. Base price USD 0.016 before Apify tier discounts. The 256 MB data-first architecture is designed for strong unit economics.
Limitations
- Analyzes supplied public or appropriately licensed data and does not bypass restricted sources.
- Scores are decision-support signals, not predictions or guarantees.
- Keep stable identifiers across snapshots for best change detection.
- Competitor evidence is refreshed before publication because the Store changes continuously.
Workflow
upstream dataset -> current snapshot -> optional previous snapshot -> normalization -> entity aggregation -> change scoring -> ranked signals -> agentAction.
