Skip to main content
Glama

aw1-circuit-breaker-remote

Server Details

Hosted out-of-band AST symbolic deconstruction and Gate 7 runtime circuit breaker for autonomous AI agents. Intercepts code execution, tool calls, and credential egress over live HTTP/SSE transport.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2024-11-05
URL
ChatGPT
–
Claude
–

TDQS

B3.2/5.0

Scored across 4 tools

Disambiguation4/5

Each tool has a recognizable role: preflight (dry-run scoring), execute (guarded run), audit lookup (fetch receipt summary), and attestation verify (validate TEE token). Some overlap exists between aw1_audit_dossier_lookup and aw1_verify_tee_attestation since both read the same SQLite ledger, but the distinction between retrieving a dossier and verifying a token is reasonably clear.

Naming Consistency3/5

All tools share the aw1_ prefix and snake_case, which is good. However, verb placement is inconsistent: aw1_execute_protected_tool and aw1_verify_tee_attestation are verb-first, while aw1_audit_dossier_lookup is noun+verb and aw1_static_ast_preflight is modifier+noun with no leading verb.

Tool Count4/5

Four tools is a tight, focused surface for a narrow security/execution gate, with each tool covering a distinct stage (preflight, execute, audit, verify). It is slightly lean but not inappropriately so for this scope.

Completeness4/5

The core lifecycle — preflight, guarded execution, audit receipt lookup, and attestation verification — is covered. Minor gaps exist: no tool to list or enumerate past audit receipts, inspect the governance ledger broadly, or discover supported protected tools/capabilities, which agents would likely want.

Publisher details

Operator
Laveto Labs · Publisher source
Vendor relationship
First-party · Publisher source
Privacy policy
Not provided
Restrictions
Community Tier free up to 30 requests/minute. Commercial/Pro enterprise tiers require an API key or token burn settlement. · Publisher source

Available Tools

4 tools
aw1_audit_dossier_lookupB
Read-onlyIdempotent
Inspect

Queries an LWA-* governance audit receipt from the tamper-evident SQLite ledger and returns its cryptographic provenance summary. Supports x402 per-call payment ($0.001/call in Base USDC).

Inputs: dossier_id (required). Returns: found, status, dossier_id

aw1_execute_protected_toolCInspect

Deterministic AST deconstruction and Gate 7 runtime circuit breaker preventing rogue shell escapes, dynamic eval(), and covert lateral socket egress in autonomous LLM tool calls.

Inputs: payload (required), tool_name (required), agent_id. Returns: status, attestation_id, execution_token

aw1_static_ast_preflightA
Read-onlyIdempotent
Inspect

Deterministic dry-run AST and Gate 7 safety preflight scoring for proposed Python or shell payloads without executing or mutating state. Supports x402 per-call payment ($0.002/call in Base USDC).

Inputs: payload (required), language. Returns: safe, findings, risk_score

aw1_verify_tee_attestationA
Read-onlyIdempotent
Inspect

Cryptographically verifies an ephemeral TEE execution token against the tamper-evident SQLite governance ledger. Supports x402 per-call payment ($0.001/call in Base USDC).

Inputs: attestation_id (required). Returns: valid, timestamp

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources