Rank clinical trials for a structured patient profile across ANY condition (oncology, cardiology, rare disease, Parkinson's, etc.). Sourced from the universal CT.gov mirror; Parkinson's-curated AI summaries appear when available. Hard disqualifiers (drop trials entirely): age out of eligibility w...
Risk signalsHigh parameter count (28 properties)
Part of the TRIALPATH server.
Free to start. No card required.
AI agents may call match_patient to permanently remove or destroy resources in TRIALPATH. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call match_patient in a loop, permanently destroying resources in TRIALPATH. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"match_patient"
]
}See the full TRIALPATH policy for all 14 tools.
These attack patterns abuse exactly the kind of access match_patient gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Rank clinical trials for a structured patient profile across ANY condition (oncology, cardiology, rare disease, Parkinson's, etc.). Sourced from the universal CT.gov mirror; Parkinson's-curated AI summaries appear when available. Hard disqualifiers (drop trials entirely): age out of eligibility window, sex mismatch, healthy-volunteer mismatch, and any comorbidity / priorTreatment / excludeTerm hit in the trial's exclusion-criteria block. Remaining trials get a normalized 0..1 fit score across the dimensions you supply: location, travel, sex, biomarkers, placebo tolerance, phase, study type, sponsor preference, drug classes, intervention kinds, performance status, required terms. The maxScore grows with the dimensions supplied so two callers with different detail can be compared. $0.10 per call (free under daily quota).. It is categorised as a Destructive tool in the TRIALPATH MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TRIALPATH MCP server in PolicyLayer and add a rule for match_patient: 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 TRIALPATH. Nothing to install.
match_patient is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the match_patient 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 match_patient. 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.
match_patient is provided by the TRIALPATH MCP server (spencerdgarrett/TRIALPATH). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 TRIALPATH 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.