Skip to main content
Glama

ZEAM :: Prism

by com.zeamprism
OverviewDiscussionsAdmin

Read the handshake and tool contract

attest_contract
Read-onlyIdempotent

Returns the handshake and contract of one MCP endpoint: initialize (protocol, server, capabilities, latency), what a plain GET returns, and tools/list rendered to a canonical snapshot with a stable hash, its context footprint in bytes and approximate tokens (total, per tool, top-3 share), an annotation audit (destructiveHint present, absent or true), naming pattern, and which tools carry examples. Keep the answer: attest_drift compares it to a later one. It makes three requests to the server named and takes as long as they take, up to 15 s each: a request not answered by then is reported timed_out, never as the server's answer. A call cut for time returns nothing. Paid, on a line: $0.000001 per millisecond. With no wallet code, ZEAM :: Pass buys the time and opens the line: a pass (https://mcp.zeamprism.com/pass) or your own wallet (https://mcp.zeamprism.com/how-to-pay). Example: {"url":"https://mcp.zeamprism.com/mcp"}

Input Schema

NameRequiredDescriptionDefault
urlYesstring — the MCP endpoint, absolute http(s) URL, e.g. https://host/mcp. Private and internal names and addresses are refused.
lineNoOptional. A line credential, for a client that cannot send the x-line header or _meta["zeam-pass/line"]: the call runs on that line's time.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "properties": {
-      "at": {
-        "anyOf": [
-          {
-            "description": "ISO time of the run",
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "contract": {
-        "anyOf": [
-          {
-            "description": "hash, tool names, footprint (bytes, approx tokens, per tool, top-3 share), annotations, naming, examples, snapshot",
-            "properties": {},
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "error": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "evidence": {
-        "anyOf": [
-          {
-            "description": "every request made, in the order sent: method, url, request headers of note, status, ms; a request that drew no answer has status 0 and its error, a redirect followed is listed in redirects, and a request still unanswered when a report was cut has unanswered: true",
-            "items": {},
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "get": {
-        "anyOf": [
-          {
-            "description": "what a plain browser GET of the endpoint returns: redirect | event-stream | html | method-not-allowed | ...",
-            "properties": {},
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "handshake": {
-        "anyOf": [
-          {
-            "description": "initialize: status, content type, protocol version, server name/version, capabilities, instructions bytes, ms, session id present",
-            "properties": {},
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "ok": {
-        "anyOf": [
-          {
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "url": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "required": [
-      "error"
-    ],
-    "type": "object"
-  },
-  {
-    "required": [
-      "accepts"
-    ],
-    "type": "object"
-  },
-  {
-    "required": [
-      "receipt"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "properties": {
+      "at": {
+        "anyOf": [
+          {
+            "description": "ISO time of the run",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "contract": {
+        "anyOf": [
+          {
+            "description": "hash, tool names, footprint (bytes, approx tokens, per tool, top-3 share), annotations, naming, examples, snapshot",
+            "properties": {},
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "error": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "evidence": {
+        "anyOf": [
+          {
+            "description": "every request made, in the order sent: method, url, request headers of note, status, ms; a request that drew no answer has status 0 and its error; one this shelf stopped has status null and says why: timed_out with limit_ms (no answer in 15 s), too_large with limit_bytes, or canceled; a redirect followed is listed in redirects, and a request still unanswered when a report was cut has unanswered: true",
+            "items": {},
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "get": {
+        "anyOf": [
+          {
+            "description": "what a plain browser GET of the endpoint returns: redirect | event-stream | html | method-not-allowed | ..., or timed_out with limit_ms",
+            "properties": {},
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "handshake": {
+        "anyOf": [
+          {
+            "description": "initialize: status, content type, protocol version, server name/version, capabilities, instructions bytes, ms, session id present",
+            "properties": {},
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ok": {
+        "anyOf": [
+          {
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "accepts"
+    ],
+    "type": "object"
+  },
+  {
+    "required": [
+      "receipt"
+    ],
+    "type": "object"
+  }
+]
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/openWorld annotations: three outbound requests with a 15 s per-request cap, a timed-out request reported as timed_out rather than as the server's answer, and a cut call returning nothing. It also discloses cost ($0.000001 per millisecond) and the payment prerequisite including where to obtain a pass.

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?

Front-loads what is returned, then the retention rule, then runtime behavior, then pricing and payment. Dense but every clause carries operational information (timeouts, cost, payment paths) rather than restating the name.

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?

Despite an output schema existing, the definition still covers the things a caller must know to invoke it correctly: per-request timeout, failure semantics, cost meter, and payment requirement. Nothing material is left to inference for a two-parameter, network-touching, paid read.

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?

Schema coverage is 100%, so baseline is 3; the description adds value by naming the endpoint example and by explaining the billing dimension of the call — 'with no wallet code, ZEAM :: Pass buys the time and opens the line' — which gives the `line` parameter real meaning beyond its schema text.

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 and resource — 'Returns the handshake and contract of one MCP endpoint' — then enumerates the payload (initialize, plain GET, tools/list snapshot, hash, token footprint, annotation audit). It explicitly positions itself against the sibling that consumes its output: 'Keep the answer: attest_drift compares it to a later one.'

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?

Gives clear situational context: run this, retain the result because attest_drift diffs against a later one, and it must be paid for via a pass or own wallet. It does not say when NOT to use it versus the other attest_* siblings, so it stops short of full routing guidance.

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

All ZEAM :: Prism 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