Skip to main content
Glama

Probe V0

by io.github.lexbritten

Verify Live HTTP Claim

verify_http_claim
Read-onlyIdempotent

Use this to verify a current public HTTPS claim by direct observation rather than web search, documentation, browser inference, or shell/curl. Use for explicit assertions that a GET/HEAD currently returns an expected HTTP status, exact header value, JSON value at a JSON Pointer, or body substring. It evaluates assertions, persists bounded evidence, reuses sufficiently fresh matching evidence, and summarizes recent observations. follow_redirects defaults to false; when true, Probe manually follows at most 3 validated HTTPS redirects. Every fetch uses redirect: manual. V0 supports only public HTTPS URLs without credentials, query strings, fragments, IP literals, or non-443 ports. Redirect validation is hostname/policy based; the Worker cannot guarantee protection against DNS rebinding between validation and platform DNS resolution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesPublic HTTPS URL to observe. V0 forbids credentials, query strings, fragments, IP literals, private or local destinations, and non-443 ports.
methodNoHTTP method to observe. Use HEAD only when response headers and status are sufficient.GET
assertionsYesOne to eight explicit assertions evaluated against the same HTTP response.
follow_redirectsNoWhether to follow up to three validated HTTPS redirects. Defaults to false.
freshness_secondsNoMaximum acceptable age of reusable matching evidence, in seconds. Public Probe V0 requires exactly 300.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
summaryYes
protocolYes
evidence_sourceYes
evidence_age_secondsYes

Schema Changelog

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

  1. Changed7 schema fields changed
    • addedInput schema / properties / assertions / description
      Added value: +"One to eight explicit assertions evaluated against the same HTTP response."
    • changedInput schema / properties / assertions / items / oneOf
      Previous value: -[
-  {
-    "properties": {
-      "expected": {
-        "maximum": 599,
-        "minimum": 100,
-        "type": "integer"
-      },
-      "kind": {
-        "const": "status",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "expected"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "expected": {
-        "maxLength": 1024,
-        "type": "string"
-      },
-      "key": {
-        "maxLength": 80,
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "header_equals",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "key",
-      "expected"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "expected": {},
-      "key": {
-        "maxLength": 256,
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "json_equals",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "key",
-      "expected"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "expected": {
-        "maxLength": 256,
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "body_contains",
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "expected"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "properties": {
+      "expected": {
+        "description": "Expected HTTP status code from 100 through 599.",
+        "maximum": 599,
+        "minimum": 100,
+        "type": "integer"
+      },
+      "kind": {
+        "const": "status",
+        "description": "Assert the HTTP response status code.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "expected"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "expected": {
+        "description": "Exact expected response header value.",
+        "maxLength": 1024,
+        "type": "string"
+      },
+      "key": {
+        "description": "Response header name to compare case-insensitively.",
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "header_equals",
+        "description": "Assert an exact response header value.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "key",
+      "expected"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "expected": {
+        "description": "Exact JSON value expected at the JSON Pointer."
+      },
+      "key": {
+        "description": "JSON Pointer identifying the response value to compare, for example /status.",
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "json_equals",
+        "description": "Assert an exact JSON value at a JSON Pointer.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "key",
+      "expected"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "expected": {
+        "description": "Literal case-sensitive substring expected in the bounded response body.",
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "const": "body_contains",
+        "description": "Assert that the response body contains a literal substring.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "expected"
+    ],
+    "type": "object"
+  }
+]
    • addedInput schema / properties / follow_redirects / description
      Added value: +"Whether to follow up to three validated HTTPS redirects. Defaults to false."
    • addedInput schema / properties / freshness_seconds / description
      Added value: +"Maximum acceptable age of reusable matching evidence, in seconds. Public Probe V0 requires exactly 300."
    • addedInput schema / properties / method / description
      Added value: +"HTTP method to observe. Use HEAD only when response headers and status are sufficient."
    • changedInput schema / properties / url / description
      Previous value: -"Public HTTPS URL. V0 forbids credentials, query strings, redirects, IP literals, and non-443 ports."New value: +"Public HTTPS URL to observe. V0 forbids credentials, query strings, fragments, IP literals, private or local destinations, and non-443 ports."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "evidence_age_seconds": {
+      "type": "number"
+    },
+    "evidence_source": {
+      "enum": [
+        "cached",
+        "fresh_execution"
+      ],
+      "type": "string"
+    },
+    "protocol": {
+      "const": "probe.check.v0",
+      "type": "string"
+    },
+    "result": {
+      "additionalProperties": false,
+      "properties": {
+        "assertion_results": {
+          "items": {
+            "anyOf": [
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "actual": {
+                    "type": "number"
+                  },
+                  "expected": {
+                    "type": "number"
+                  },
+                  "kind": {
+                    "const": "status",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "expected",
+                  "actual",
+                  "passed"
+                ],
+                "type": "object"
+              },
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "actual_fingerprint": {
+                    "additionalProperties": false,
+                    "properties": {
+                      "sha256": {
+                        "type": "string"
+                      },
+                      "type": {
+                        "type": "string"
+                      }
+                    },
+                    "required": [
+                      "type",
+                      "sha256"
+                    ],
+                    "type": "object"
+                  },
+                  "expected": {
+                    "type": "string"
+                  },
+                  "key": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "const": "header_equals",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "key",
+                  "expected",
+                  "actual_fingerprint",
+                  "passed"
+                ],
+                "type": "object"
+              },
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "error_code": {
+                    "type": "string"
+                  },
+                  "expected": {
+                    "type": "string"
+                  },
+                  "key": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "const": "header_equals",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "const": false,
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "key",
+                  "expected",
+                  "passed",
+                  "error_code"
+                ],
+                "type": "object"
+              },
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "actual_fingerprint": {
+                    "additionalProperties": false,
+                    "properties": {
+                      "sha256": {
+                        "type": "string"
+                      },
+                      "type": {
+                        "type": "string"
+                      }
+                    },
+                    "required": [
+                      "type",
+                      "sha256"
+                    ],
+                    "type": "object"
+                  },
+                  "expected": {},
+                  "key": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "const": "json_equals",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "key",
+                  "expected",
+                  "actual_fingerprint",
+                  "passed"
+                ],
+                "type": "object"
+              },
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "error_code": {
+                    "type": "string"
+                  },
+                  "expected": {},
+                  "key": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "const": "json_equals",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "const": false,
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "key",
+                  "expected",
+                  "passed",
+                  "error_code"
+                ],
+                "type": "object"
+              },
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "contains": {
+                    "type": "boolean"
+                  },
+                  "expected": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "const": "body_contains",
+                    "type": "string"
+                  },
+                  "passed": {
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "expected",
+                  "contains",
+                  "passed"
+                ],
+                "type": "object"
+              }
+            ]
+          },
+          "type": "array"
+        },
+        "body_sha256": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "body_truncated": {
+          "type": "boolean"
+        },
+        "bytes_observed": {
+          "type": "number"
+        },
+        "error_code": {
+          "type": "string"
+        },
+        "final_url": {
+          "type": "string"
+        },
+        "latency_ms": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "observed_at": {
+          "type": "string"
+        },
+        "probe_id": {
+          "type": "string"
+        },
+        "protocol": {
+          "const": "probe.evidence.v0",
+          "type": "string"
+        },
+        "redirect_chain": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "from_url": {
+                "type": "string"
+              },
+              "hop": {
+                "type": "number"
+              },
+              "location": {
+                "type": "string"
+              },
+              "rejection": {
+                "type": "string"
+              },
+              "resolved_url": {
+                "type": "string"
+              },
+              "status_code": {
+                "type": "number"
+              },
+              "validated": {
+                "type": "boolean"
+              }
+            },
+            "required": [
+              "hop",
+              "from_url",
+              "status_code",
+              "validated"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "redirect_count": {
+          "type": "number"
+        },
+        "redirects_followed": {
+          "type": "boolean"
+        },
+        "status_code": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "target": {
+          "additionalProperties": false,
+          "properties": {
+            "host": {
+              "type": "string"
+            },
+            "method": {
+              "enum": [
+                "GET",
+                "HEAD"
+              ],
+              "type": "string"
+            }
+          },
+          "required": [
+            "host",
+            "method"
+          ],
+          "type": "object"
+        },
+        "termination": {
+          "type": "string"
+        },
+        "verdict": {
+          "enum": [
+            "PASS",
+            "FAIL",
+            "ERROR"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "protocol",
+        "probe_id",
+        "observed_at",
+        "verdict",
+        "target",
+        "status_code",
+        "latency_ms",
+        "body_sha256",
+        "bytes_observed",
+        "body_truncated",
+        "assertion_results",
+        "redirects_followed",
+        "redirect_count",
+        "final_url",
+        "redirect_chain",
+        "termination"
+      ],
+      "type": "object"
+    },
+    "summary": {
+      "additionalProperties": false,
+      "properties": {
+        "agreement": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "changed_since_previous": {
+          "type": "boolean"
+        },
+        "counts": {
+          "additionalProperties": false,
+          "properties": {
+            "ERROR": {
+              "type": "number"
+            },
+            "FAIL": {
+              "type": "number"
+            },
+            "PASS": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "PASS",
+            "FAIL",
+            "ERROR"
+          ],
+          "type": "object"
+        },
+        "dominant_verdict": {
+          "anyOf": [
+            {
+              "enum": [
+                "PASS",
+                "FAIL"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "observations": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "observations",
+        "counts",
+        "dominant_verdict",
+        "agreement",
+        "changed_since_previous"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "protocol",
+    "evidence_source",
+    "evidence_age_seconds",
+    "result",
+    "summary"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already signal read-only, open-world, and idempotent behavior, so the description adds substantial context beyond them: it evaluates assertions, persists bounded evidence, reuses sufficiently fresh matching evidence, summarizes recent observations, defaults follow_redirects to false, manually follows at most three validated HTTPS redirects, uses redirect: manual on every fetch, and warns about DNS rebinding limitations. This is exemplary behavioral disclosure.

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

Conciseness5/5

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

The description is dense but every sentence contributes new information: purpose, assertion types, caching/evidence behavior, redirect mechanics, URL restrictions, and a security caveat. It is front-loaded with the primary use case and maintains a logical flow from high-level intent to low-level operational details without redundancy.

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 tool with five parameters, a non-trivial assertion schema, and an output schema, the description covers all relevant operational context: why to use it, what assertions it supports, how redirects and evidence reuse behave, what URL forms are allowed, and a security limitation. Nothing essential to correct invocation is omitted.

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 each parameter is already documented in the schema. The description adds useful operational color, especially for follow_redirects ('Probe manually follows at most 3 validated HTTPS redirects') and for url constraints ('without credentials, query strings, fragments, IP literals, or non-443 ports'), but it does not need to and does not deeply elaborate on the assertion structure, since the schema already defines that.

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 begins with a specific verb and resource: 'verify a current public HTTPS claim by direct observation.' It clearly enumerates the assertion types (HTTP status, exact header value, JSON value at a JSON Pointer, body substring) and explicitly contrasts itself with web search, documentation, browser inference, and shell/curl, making the tool's unique role unmistakable.

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 gives explicit when-to-use guidance: 'Use for explicit assertions that a GET/HEAD currently returns...' and lists alternatives to avoid ('rather than web search, documentation, browser inference, or shell/curl'). It also conveys constraints on supported URLs and redirects. However, it does not directly address the sibling tool probe.history, leaving the boundary with historical evidence lookup implicit rather than explicit.

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

All Probe V0 toolsInspect
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

verify_http_claim performs live current verification while probe.history retrieves persisted past observations. The descriptions explicitly separate the two use cases, so an agent should not confuse them.

Naming Consistency3/5

verify_http_claim follows a verb_object pattern, while probe.history uses a namespace.noun pattern. Both names are readable and lowercase, but the two naming styles are mixed rather than following one predictable convention.

Tool Count3/5

With only two tools the surface feels thin, but the narrow purpose of live HTTP verification plus historical evidence lookup is served without unnecessary additions. The minimal count is appropriate but borderline on the calibration scale.

Completeness4/5

The core workflow is covered: verify a claim with current evidence and later inspect the persisted history. Minor gaps such as listing or clearing experiments are absent but not required for the stated verification loop.

Resources