Skip to main content
Glama

ProofRail MCP Release Certifier

by io.github.kaattaallaa-sketch
OverviewDiscussionsAdmin

mcp_release_certify

Paid MCP server verification and certification with deployment contract checks: require named tools with required_tools, compare baseline_schema_hashes from a previous certification, and receive ALLOW/BLOCK/REVIEW evidence. Certification before deploy, upgrade, or trust. Returns deterministic PASS, FAIL, or PARTIAL evidence. Call with target_url; when payment is absent the x402 layer returns payment requirements/challenge, then the client pays and retries the same call. Use mcp_release_preflight first for a free no-payment compatibility check, or quote_certification(target_url) for an exact buy_now action.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixture_idNoOptional server-configured safe fixture id; callers cannot provide arbitrary tool arguments
target_urlYesPublic MCP Streamable HTTP endpoint to certify before deployment or integration
check_profileNoVerification profile; basic covers connection, protocol negotiation, tools/list, and schemasbasic
required_toolsNoPaid integration gate: fail if any named tool is missing.
baseline_schema_hashesNoPaid drift check: prior contract_baseline; removed tools fail, changed input-schema hashes require review.
declared_protocol_versionNoMCP protocol version the target release claims to support

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / baseline_schema_hashes
      Added value: +{
+  "additionalProperties": {
+    "pattern": "^[a-f0-9]{64}$",
+    "type": "string"
+  },
+  "description": "Paid drift check: prior contract_baseline; removed tools fail, changed input-schema hashes require review.",
+  "propertyNames": {
+    "maxLength": 128,
+    "minLength": 1
+  },
+  "type": "object"
+}
    • addedInput schema / properties / required_tools
      Added value: +{
+  "description": "Paid integration gate: fail if any named tool is missing.",
+  "items": {
+    "maxLength": 128,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}
  2. Changed4 schema fields changed
    • addedInput schema / properties / check_profile / description
      Added value: +"Verification profile; basic covers connection, protocol negotiation, tools/list, and schemas"
    • addedInput schema / properties / declared_protocol_version / description
      Added value: +"MCP protocol version the target release claims to support"
    • addedInput schema / properties / fixture_id / description
      Added value: +"Optional server-configured safe fixture id; callers cannot provide arbitrary tool arguments"
    • addedInput schema / properties / target_url / description
      Added value: +"Public MCP Streamable HTTP endpoint to certify before deployment or integration"
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden well: it discloses the paid x402 flow (payment requirements/challenge, then client pays and retries the same call) and the deterministic ALLOW/BLOCK/REVIEW and PASS/FAIL/PARTIAL evidence semantics. It stops short of stating auth/permission prerequisites or rate limits, but payment behavior is unusually well documented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the preflight alternative are front-loaded before the payment mechanics, and every sentence carries information. It is dense and somewhat packed into one long block, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-param paid tool with no output schema and no annotations, the description covers payment flow, expected evidence outcomes, and prerequisite alternatives. Minor gaps remain around permissions and return payload shape, but it is largely self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already defines every parameter including the required_tools gate and baseline_schema_hashes drift check. The description reinforces their purpose ('require named tools', 'compare baseline_schema_hashes from a previous certification') but adds no syntax or format detail beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('MCP server verification and certification') plus the deployment contract scope, and explicitly names what distinguishes it from siblings (preflight, quote_certification). An agent can identify this as the paid certification tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit triggers ('certification before deploy, upgrade, or trust') and names the alternatives with the condition that selects them ('Use mcp_release_preflight first for a free no-payment compatibility check, or quote_certification(target_url)'). Routing is fully specified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ProofRail MCP Release Certifier toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources