agentguard — policy proxy for agent tool calls
https://agentwares-agentguard.vercel.app/api/mcp ↗
Description
Manage hosted agentguard proxies: caps, dry-run, loop breaker, run reports, audit export.
What our measurements say
agentguard — policy proxy for agent tool calls is a remote MCP server published at agentwares-agentguard.vercel.app. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 325 ms, placing it among the faster endpoints. It offers a narrow, focused set of 6 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names explicitly indicate their purpose (e.g., 'agentguard_create_proxy').
- Descriptions include account key requirements and specific use cases (e.g., audit export).
Weaknesses
- Descriptions often omit when tools should be used, focusing only on functionality.
- Parameter names and types are sometimes ambiguous (e.g., 'policyYaml' lacks format details).
- No explicit error handling or constraint documentation for edge cases.
agentguard_get_pricing— Dense technical jargon without context for non-experts.agentguard_set_policy— Parameter 'policyYaml' lacks format specification (e.g., YAML schema).agentguard_recommend_allowlist— Mentions 'apply in dashboard' but doesn't clarify integration steps.
Verdict
Event narrative
Sign up free to generateRaw observations
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 161ms → warm 165ms (penalty 0ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
agentguard_get_pricingMachine-readable pricing for agentguard hosted: bands (Starter/Pro/Team) with included tool calls per month, the 80% soft alert and 150% hard stop, features, the free trial allowance, and `per_call` — buying tool calls outright at POST /api/v1/calls from a prepaid balance, which is the one purchase here an unattended agent can complete. Same data as /pricing.json.
agentguard_create_proxyCreate a hosted agentguard proxy in front of an MCP server. Returns the proxy id, the per-customer MCP URL and the proxy key (shown once). Point your agent's MCP client at the URL with `Authorization: Bearer <key>`. Requires an account key.
slugstringrequiredupstreamUrlstringrequiredupstreamNamestringmodestring
agentguard_set_policyReplace a proxy's policy (YAML: mode, upstreams, classify, caps, loop, dry_run, approvals, alerts, chaos, drift). Validated before saving; takes effect within 30 seconds. Requires an account key.
proxyIdstringrequiredpolicyYamlstringrequired
agentguard_get_runThe incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.
proxyIdstringrequiredrunIdstringrequired
agentguard_export_auditExport a run's hash-chained audit entries (prev_hash, hash, redacted args) with the Merkle root, for disputes and questionnaires. Verify offline with sha256(prev_hash + canonical(entry)). Requires an account key.
proxyIdstringrequiredrunIdstringrequired
agentguard_recommend_allowlistLeast-privilege recommendation from the proxy's recorded calls: the minimal tool allowlist, argument keys used per tool, and the upstream tools never used (remove them first). No LLM call here; apply it in the dashboard. Requires an account key.
proxyIdstringrequired
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Legacy
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-agentwares-agentguard-cloud)<a href="https://mcpmetrics.io/servers/io-github-agentwares-agentguard-cloud"><img src="https://mcpmetrics.io/badge/io.github.agentwares/agentguard-cloud/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- datamcp — Hosted Model Context Protocol for Databases, APIs, and Agent Memoryapi.datamcp.app
PostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.
- AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliancemcp.agenticrail.nz
Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.
- Verdigraph — paid hosted MCP for compute routingverdigraph-mcp.hartjustin6.workers.dev
Paid hosted MCP for agent-to-agent compute routing. 25% of net revenue funds conservation.
- agent-memory-apiagent-memory-api-bix5.onrender.com
Solves memory loss for AI agents operating across multiple calls. Store, recall and audit long-term memory with AES-256 encryption. Includes SHA256 deletion audit proof. x402 USDC pay-per-call. Japanese language support included.
- Jobly — Agent-to-Agent Contract Marketplaceusejobly.xyz
Post contracts, submit proposals, negotiate terms, and resolve disputes on Jobly — an agent-to-agent contract marketplace. Every contract requires structured acceptance criteria, making "did they deliver?" answerable from a spec. Disputes go through AI verdict → appeal window → community stake vote before escrow moves. **29 tools covering the full contract lifecycle:** - Register/login and get an API key - Post contracts with structured terms (scope, deliverables, acceptance criteria) - Browse open contracts and submit proposals - Negotiate via counter-offers - Submit and review deliverables - Release escrow or raise disputes - Appeal AI verdicts and vote on community disputes - Manage provider profiles, messages, and reviews All transactions use JOOBs (sandbox currency). Free to use.
- Socializioz AI Social Media Agent MCPsocializioz.com
SocializioZ is an AI-powered social media management platform — it connects your social accounts (Instagram, Facebook, TikTok, X, LinkedIn, Telegram) and lets you create content, generate images/videos, schedule and publish posts, run campaigns, and track performance, all from one place with an AI agent handling the execution.
Comments
Sign in to write a comment
No comments yet. Be the first.