Agent Trust Firewall
Server Details
Free pre-action policy checks and data cleaning for autonomous AI agents.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
The three check tools overlap because trust_check_action subsumes spend and data checks, but descriptions explicitly route budget-only work to trust_check_spend and structure-only work to trust_validate_data. trust_clean_data and trust_get_capabilities are clearly distinct, leaving only minor risk when choosing composite versus focused checks.
All five names follow the same trust_ prefix plus verb_noun pattern in snake_case: check_action, check_spend, clean_data, get_capabilities, validate_data. There are no mixed conventions or vague standalone verbs.
Five tools are well-scoped for a stateless pre-execution firewall. Each tool has a clear role: composite gate, spend check, data validation, data cleaning, and capability discovery.
The surface covers the core lifecycle: discover capabilities, validate structure, clean data, check spend, and run the composite action gate. Minor gaps are that evidence/source checks exist only inside trust_check_action and there is no standalone policy/history tool, though those limitations are explicitly by design for this stateless pilot.
Available Tools
5 toolstrust_check_actionCheck an action against inline policyARead-onlyIdempotentInspect
Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks must pass: evidence cannot override an over-budget payment. Set action.type to payment to activate spending checks and pass its amount with remaining_budget; contract applies to data, not action. Use this gate before execution, trust_check_spend for budget alone, or trust_validate_data for structure alone. Enforce BLOCK and fail closed on errors. Source labels are unauthenticated; instruction scanning is a limited phrase heuristic. No action execution, wallet access, policy storage or decision history. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Inputs: action (required), data, contract, evidence, +7 more. Returns: Structured result, also serialized in the text content block.
trust_check_spendCheck a proposed spend against limitsARead-onlyIdempotentInspect
Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are independent: amount=4, remaining_budget=10, per_transaction_limit=3 returns BLOCK; equality passes. Use one currency/unit, and update remaining_budget in your application after each actual purchase: this tool neither tracks cumulative spending nor converts currencies. Omitting allowed_merchants skips merchant checks; supplying it requires an exact merchant match, and [] blocks all merchants. Use trust_check_action to include evidence or data checks. Enforce BLOCK before paying; this tool never accesses a wallet or executes payment. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Inputs: amount (required), remaining_budget (required), merchant, allowed_merchants, +1 more. Returns: Structured result, also serialized in the text content block.
trust_clean_dataAudit and clean JSON rowsARead-onlyIdempotentInspect
Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplication, then required/range checks: keys " a " and "a" collide after trimming. Duplicate removal keeps the first row and skips later-row field checks; missing keys are retained and flagged. REVIEW persists even after repair, so inspect issues before use; [] returns ALLOW. Numeric strings are not converted or range-checked; use trust_validate_data for type enforcement. Only top-level strings are trimmed; inputs are not mutated. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Inputs: rows (required), primary_key, trim_strings, numeric_ranges, +2 more. Returns: Structured result, also serialized in the text content block.
trust_get_capabilitiesDiscover limits and the stateless workflowARead-onlyIdempotentInspect
Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory endpoint accepts no action, policy or filter arguments; use tools/list for callable schemas and trust_check_action for a verdict. The response explains enforcement and limitations, not stored policy or decision history: rules must accompany each check. Free and unauthenticated, with operational usage metadata recorded but no request-body storage. Re-read after a deployment to detect capability changes.
Inputs: no named parameters. Returns: Structured result, also serialized in the text content block.
trust_validate_dataValidate JSON field constraintsARead-onlyIdempotentInspect
Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine required:true, type:"integer" and min:1 for a positive mandatory quantity: min alone neither requires a value nor rejects numeric strings. Missing, null or empty optional values skip the other constraints; 0 and false do not. For nested data, fields["order.total"] addresses a leaf; allow_extra:false compares top-level keys, so keep it true for dot-path rules. Use trust_clean_data for transformations or trust_check_action for evidence/spending checks. This validates structure, not facts or provenance. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Inputs: data (required), fields (required), allow_extra. Returns: Structured result, also serialized in the text content block.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls.
Paid deterministic data-quality and execution-verification tools for AI agents.
Free pre-execution contract checks for AI agents: preflight, control-plane scans, EAS anchors.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA free, local check before your AI agent acts: every tool action is checked against your YAML rules and returns ACT, BLOCK or ESCALATE with an audit record. Optional: send escalations to Flow for a judgment.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables autonomous AI agents to operate safely by intercepting risky tool calls, evaluating them against policy, and suspending them for human approval via Slack, Telegram, or a web dashboard.2Apache 2.0
- AlicenseAqualityCmaintenanceRuntime policy enforcement for AI agents. Evaluate every agent action against your organization's policies before execution, with observe and enforce modes.11MIT
- AlicenseNot gradedqualityDmaintenanceEnables deterministic zero-trust security for AI agents, providing prompt injection protection, PII scrubbing, and policy enforcement before agentic actions reach production systems.2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.