Server definition

Hash: sha256:55ee61d5c3bf04f3fa7bc3d52fba3d246b231e1d5963f7a9cff30f1296d0ac5f
What it is: What a remote MCP server returned when asked what it offers: 7 tools

The blob, as servednamed by its sha256

{
  "instructions": "agentguard hosted: a policy proxy between agents and their MCP servers (loop breaker, caps, dry-run, kill switch, hash-chained audit). agentguard_spend_report and agentguard_get_pricing need no key: post an agent log to the first and it names the band whose cap would have stopped each overspend, which is the cheapest way to find out whether this is worth paying for. The other tools need an account key (Authorization: Bearer ak_...); POST https://agentwares-agentguard.vercel.app/api/v1/signup with {\"accept_terms\": true} to get one and start the free trial, with no human and no card. A browser dashboard exists at https://agentwares-agentguard.vercel.app/dashboard but is not required. Create a proxy, point the agent at the returned mcpUrl with its key, then read runs with agentguard_get_run.",
  "tools": [
    {
      "description": "Create 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.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "mode": {
            "default": "dry-run",
            "description": "dry-run records what the policy would have blocked and lets every call through; enforce actually blocks. Start in dry-run.",
            "enum": [
              "dry-run",
              "enforce"
            ],
            "type": "string"
          },
          "slug": {
            "description": "short name, a-z 0-9 -",
            "maxLength": 40,
            "minLength": 2,
            "type": "string"
          },
          "upstreamName": {
            "description": "name used to namespace tools when you add more upstreams later",
            "maxLength": 32,
            "minLength": 1,
            "type": "string"
          },
          "upstreamUrl": {
            "description": "Streamable HTTP URL of the MCP server to protect",
            "format": "uri",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "upstreamUrl"
        ],
        "type": "object"
      },
      "name": "agentguard_create_proxy",
      "outputSchema": null
    },
    {
      "description": "Export a run's hash-chained audit entries (prev_hash, hash, redacted args) with the Merkle root, for disputes and questionnaires. Verify offline with sha256(prev_hash + canonical(entry)). Requires an account key.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "proxyId": {
            "description": "the proxy id returned by agentguard_create_proxy",
            "minLength": 6,
            "type": "string"
          },
          "runId": {
            "description": "the X-Run-Id your agent sent with the calls; one run is one agent session",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "proxyId",
          "runId"
        ],
        "type": "object"
      },
      "name": "agentguard_export_audit",
      "outputSchema": null
    },
    {
      "description": "Machine-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.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "agentguard_get_pricing",
      "outputSchema": null
    },
    {
      "description": "The incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "proxyId": {
            "description": "the proxy id returned by agentguard_create_proxy",
            "minLength": 6,
            "type": "string"
          },
          "runId": {
            "description": "the X-Run-Id your agent sent with the calls; one run is one agent session",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "proxyId",
          "runId"
        ],
        "type": "object"
      },
      "name": "agentguard_get_run",
      "outputSchema": null
    },
    {
      "description": "Least-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.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "proxyId": {
            "description": "the proxy id returned by agentguard_create_proxy",
            "minLength": 6,
            "type": "string"
          }
        },
        "required": [
          "proxyId"
        ],
        "type": "object"
      },
      "name": "agentguard_recommend_allowlist",
      "outputSchema": null
    },
    {
      "description": "Replace a proxy's policy (YAML: mode, upstreams, classify, caps, loop, dry_run, approvals, alerts, chaos, drift). Validated before saving; takes effect within 30 seconds. Requires an account key.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "policyYaml": {
            "description": "the complete policy document; it replaces the current one rather than merging",
            "maxLength": 64000,
            "minLength": 1,
            "type": "string"
          },
          "proxyId": {
            "description": "the proxy id returned by agentguard_create_proxy",
            "minLength": 6,
            "type": "string"
          }
        },
        "required": [
          "proxyId",
          "policyYaml"
        ],
        "type": "object"
      },
      "name": "agentguard_set_policy",
      "outputSchema": null
    },
    {
      "description": "Read an agent log and report what it spent: totals, calls by tool and by class, estimated\ndollars by rail, loops, the largest single run, and — for every overspend — the agentguard\nband whose cap would have stopped it, the exact cap, and the call that would have tripped\nit.\n\nNeeds no account and no key. The log is read in the request and discarded; nothing is\nstored. Accepts an agentwares audit export (`agentwares.audit/v1`), a Claude Code session\n`.jsonl`, or a CSV/JSONL of tool calls with any of `tool`, `ts`, `class`, `amount_usd`,\n`rail`, `run_id`, `model`, `input_tokens`, `output_tokens`.\n\nCaps come from the proxy's own default policy, so a band named here refuses exactly what\nit says it refuses. Buying that band is a checkout a person completes; the calls-only\npurchase an unattended agent can complete is in `agentguard_get_pricing` instead.",
      "inputSchema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "additionalProperties": false,
        "properties": {
          "detail": {
            "description": "`concise` (default) returns the totals, the top ten tools, the rails, the loops and every overspend. `full` adds the complete per-tool breakdown and the window. Ask for `full` only when you are going to read it.",
            "enum": [
              "concise",
              "full"
            ],
            "type": "string"
          },
          "log": {
            "description": "The log itself, verbatim — JSON, JSONL or CSV. Not a path and not a URL: this server does not fetch anything.",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "log"
        ],
        "type": "object"
      },
      "name": "agentguard_spend_report",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:55ee61d5c3bf04f3fa7bc3d52fba3d246b231e1d5963f7a9cff30f1296d0ac5f | sha256sum