agent-exec

agent-exec service card

service_card

Read-only

What agent-exec sells, what it costs, and exactly where to send a plain-HTTP x402 payment to buy it. This tool call itself is free and moves no money -- MCP cannot carry an x402 402, so buying happens over plain HTTP at the URLs this returns, not through this MCP connection.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
`quote`	Yes
`execute`	Yes
`llmsTxt`	Yes
`network`	Yes
`openapi`	Yes
`payment`	Yes
`service`	Yes
`directory`	Yes
`description`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "description": {
+      "type": "string"
+    },
+    "directory": {
+      "additionalProperties": false,
+      "properties": {
+        "listEndpoint": {
+          "type": "string"
+        },
+        "listingIsFree": {
+          "type": "boolean"
+        },
+        "paidPlacement": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "duration": {
+                "type": "string"
+              },
+              "priceUsd": {
+                "type": "number"
+              }
+            },
+            "required": [
+              "duration",
+              "priceUsd"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "promoteEndpoint": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "listEndpoint",
+        "listingIsFree",
+        "paidPlacement",
+        "promoteEndpoint"
+      ],
+      "type": "object"
+    },
+    "execute": {
+      "additionalProperties": false,
+      "properties": {
+        "endpoint": {
+          "type": "string"
+        },
+        "method": {
+          "type": "string"
+        },
+        "note": {
+          "type": "string"
+        },
+        "priceUsd": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "endpoint",
+        "method",
+        "priceUsd",
+        "note"
+      ],
+      "type": "object"
+    },
+    "llmsTxt": {
+      "type": "string"
+    },
+    "network": {
+      "type": "string"
+    },
+    "openapi": {
+      "type": "string"
+    },
+    "payment": {
+      "additionalProperties": false,
+      "properties": {
+        "howToPay": {
+          "type": "string"
+        },
+        "identity": {
+          "type": "string"
+        },
+        "manifest": {
+          "type": "string"
+        },
+        "protocol": {
+          "type": "string"
+        },
+        "transport": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "protocol",
+        "transport",
+        "manifest",
+        "howToPay",
+        "identity"
+      ],
+      "type": "object"
+    },
+    "quote": {
+      "additionalProperties": false,
+      "properties": {
+        "endpoint": {
+          "type": "string"
+        },
+        "free": {
+          "type": "boolean"
+        },
+        "method": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "endpoint",
+        "method",
+        "free"
+      ],
+      "type": "object"
+    },
+    "service": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "service",
+    "description",
+    "network",
+    "execute",
+    "quote",
+    "directory",
+    "payment",
+    "openapi",
+    "llmsTxt"
+  ],
+  "type": "object"
+}

First observedSep 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations' readOnlyHint=true, the description explicitly discloses that the call itself is free, moves no money, and cannot carry an x402 402 over MCP. This is valuable behavioral context that prevents an agent from incorrectly attempting to complete a purchase through this tool.

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?

Two sentences cover purpose, cost, payment channel, and the key limitation of MCP. The description is efficient and front-loaded, though the second sentence slightly restates the plain-HTTP point already implied in the first.

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

Completeness5/5

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

For a zero-parameter, read-only informational tool with an output schema available, the description provides all critical context: what the tool returns, the fact that it is free, and the essential warning that payment must occur over plain HTTP rather than via MCP. Nothing needed for correct invocation is missing.

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

Parameters4/5

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

The tool has zero parameters, so there is nothing for the description to explain. The baseline for a parameterless tool is 4, and no additional semantic burden falls on the description.

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?

The description clearly states the tool's purpose: it returns what agent-exec sells, what it costs, and the exact URL for paying via x402. This distinguishes it from the sibling search_listings, which presumably discovers listings rather than providing purchase/payment details.

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

Usage Guidelines4/5

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

The description provides clear context: use this tool to get pricing and payment routing, and explicitly warns that actual purchase must happen over plain HTTP, not through MCP. It does not explicitly name search_listings as the alternative for browsing/finding listings, but the purpose is clear enough for correct tool selection.

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

All agent-exec tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

The two tools have clear, non-overlapping roles: search_listings handles discovery and pagination over the catalog, while service_card provides purchase details and payment instructions. There is no realistic scenario where an agent would confuse which tool to use.

Naming Consistency3/5

search_listings follows a verb_noun pattern, but service_card is a bare noun phrase and lacks an action verb like get_ or fetch_. The names are readable and distinguishable, but the conventions are mixed.

Tool Count3/5

Two tools is on the thin side for a directory-oriented server, but each tool serves a distinct step in the discover-then-purchase flow. It is a borderline count rather than well-scoped or excessive.

Completeness4/5

For the apparent consumer-facing purpose, the core loop is covered: search listings to find a service, then get the service card for pricing and payment URL. A few extras like filtering, categories, or a dedicated listing-detail tool would round it out, but there are no major dead ends.

Resources

Need Help?