Skip to main content
Glama
hedging8563

TokenLab MCP Server

by hedging8563
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Create message (Anthropic-compatible)

create_anthropic_message

Generate Claude model responses in Anthropic's native format, supporting vision, streaming, and API key authentication.

Instructions

Creates a model response using Anthropic's native request format. Supports Claude models with vision and streaming. Authentication: Use x-api-key header or Authorization: Bearer header.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYesModel to use (e.g., claude-sonnet-4-6)
toolsNoTool definitions available to the model.
top_kNo
top_pNo
systemNoSystem prompt
messagesYesMessages in the conversation
metadataNoRequest metadata echoed into downstream logs or traces when supported.
thinkingNoThinking configuration for compatible Anthropic-style models.
max_tokensYesMaximum number of tokens to generate
temperatureNo
tool_choiceNoTool choice policy or explicit tool selection.
service_tierNoService tier hint where supported by the model.
stop_sequencesNo
stream_optionsNoStreaming options such as usage chunk inclusion.
X-TokenLab-Delivery-PolicyNoPer-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.26
    • changedInput schema / properties / service_tier / description
      Previous value: -"Service tier hint for compatible providers."New value: +"Service tier hint where supported by the model."
  2. Changed1 schema field changedv0.6.24
    • addedInput schema / properties / X-TokenLab-Delivery-Policy
      Added value: +{
+  "description": "Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri…",
+  "enum": [
+    "auto",
+    "verified",
+    "official"
+  ],
+  "type": "string"
+}
  3. Changed15 schema fields changedv0.6.4
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedInput schema / properties / max_tokens / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / messages / items / additionalProperties
      Removed value: -{}
    • removedInput schema / properties / messages / items / properties / content / oneOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "additionalProperties": {},
-      "properties": {
-        "source": {
-          "additionalProperties": {},
-          "properties": {
-            "data": {
-              "type": "string"
-            },
-            "media_type": {
-              "type": "string"
-            },
-            "type": {
-              "enum": [
-                "base64",
-                "url"
-              ],
-              "type": "string"
-            },
-            "url": {
-              "type": "string"
-            }
-          },
-          "type": "object"
-        },
-        "text": {
-          "type": "string"
-        },
-        "type": {
-          "enum": [
-            "text",
-            "image"
-          ],
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "type": "array"
-  }
-]
    • changedInput schema / properties / metadata / additionalProperties
      Previous value: -{}New value: +true
    • removedInput schema / properties / metadata / properties
      Removed value: -{}
    • removedInput schema / properties / stream
      Removed value: -{
-  "const": false,
-  "default": false,
-  "description": "MCP tool calls return one final result; omit stream or set it to false.",
-  "type": "boolean"
-}
    • changedInput schema / properties / stream_options / additionalProperties
      Previous value: -{}New value: +true
    • removedInput schema / properties / stream_options / properties
      Removed value: -{}
    • changedInput schema / properties / thinking / additionalProperties
      Previous value: -{}New value: +true
    • removedInput schema / properties / thinking / properties
      Removed value: -{}
    • changedInput schema / properties / tool_choice / oneOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]
    • changedInput schema / properties / tools / items / additionalProperties
      Previous value: -{}New value: +true
    • removedInput schema / properties / tools / items / properties
      Removed value: -{}
    • removedInput schema / properties / top_k / maximum
      Removed value: -9007199254740991
  4. Changed25 schema fields changedv0.3.1
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / max_tokens / default
      Removed value: -512
    • changedInput schema / properties / max_tokens / description
      Previous value: -"Maximum output tokens."New value: +"Maximum number of tokens to generate"
    • changedInput schema / properties / messages / description
      Previous value: -"Native Anthropic conversation messages."New value: +"Messages in the conversation"
    • addedInput schema / properties / messages / items / additionalProperties
      Added value: +{}
    • removedInput schema / properties / messages / items / properties / content / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "additionalProperties": {},
-      "properties": {},
-      "type": "object"
-    },
-    "minItems": 1,
-    "type": "array"
-  }
-]
    • addedInput schema / properties / messages / items / properties / content / oneOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "additionalProperties": {},
+      "properties": {
+        "source": {
+          "additionalProperties": {},
+          "properties": {
+            "data": {
+              "type": "string"
+            },
+            "media_type": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "base64",
+                "url"
+              ],
+              "type": "string"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "text": {
+          "type": "string"
+        },
+        "type": {
+          "enum": [
+            "text",
+            "image"
+          ],
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "type": "array"
+  }
+]
    • removedInput schema / properties / messages / minItems
      Removed value: -1
    • changedInput schema / properties / metadata / description
      Previous value: -"Optional request metadata."New value: +"Request metadata echoed into downstream logs or traces when supported."
    • changedInput schema / properties / model / description
      Previous value: -"Public TokenLab Claude-compatible model ID."New value: +"Model to use (e.g., claude-sonnet-4-6)"
    • removedInput schema / properties / model / minLength
      Removed value: -1
    • removedInput schema / properties / prompt
      Removed value: -{
-  "description": "Convenience shortcut for one user text message; do not combine with messages.",
-  "minLength": 1,
-  "type": "string"
-}
    • changedInput schema / properties / service_tier / description
      Previous value: -"Optional service-tier hint."New value: +"Service tier hint for compatible providers."
    • removedInput schema / properties / stop_sequences / description
      Removed value: -"Optional stop sequences."
    • addedInput schema / properties / stream
      Added value: +{
+  "const": false,
+  "default": false,
+  "description": "MCP tool calls return one final result; omit stream or set it to false.",
+  "type": "boolean"
+}
    • addedInput schema / properties / stream_options
      Added value: +{
+  "additionalProperties": {},
+  "description": "Streaming options such as usage chunk inclusion.",
+  "properties": {},
+  "type": "object"
+}
    • changedInput schema / properties / system / description
      Previous value: -"Optional system prompt."New value: +"System prompt"
    • removedInput schema / properties / temperature / description
      Removed value: -"Optional sampling temperature."
    • changedInput schema / properties / thinking / description
      Previous value: -"Thinking configuration for compatible models."New value: +"Thinking configuration for compatible Anthropic-style models."
    • removedInput schema / properties / tool_choice / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  }
-]
    • addedInput schema / properties / tool_choice / oneOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  }
+]
    • changedInput schema / properties / tools / description
      Previous value: -"Native Anthropic tool definitions."New value: +"Tool definitions available to the model."
    • removedInput schema / properties / top_k / description
      Removed value: -"Optional top-k sampling cutoff."
    • removedInput schema / properties / top_p / description
      Removed value: -"Optional nucleus sampling probability."
    • changedInput schema / required
      Previous value: -[
-  "model"
-]New value: +[
+  "model",
+  "max_tokens",
+  "messages"
+]
  5. Changed13 schema fields changedv0.3.0
    • changedInput schema / properties / max_tokens / maximum
      Previous value: -8192New value: +9007199254740991
    • addedInput schema / properties / messages
      Added value: +{
+  "description": "Native Anthropic conversation messages.",
+  "items": {
+    "properties": {
+      "content": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "items": {
+              "additionalProperties": {},
+              "properties": {},
+              "type": "object"
+            },
+            "minItems": 1,
+            "type": "array"
+          }
+        ]
+      },
+      "role": {
+        "enum": [
+          "user",
+          "assistant"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "role",
+      "content"
+    ],
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}
    • addedInput schema / properties / metadata
      Added value: +{
+  "additionalProperties": {},
+  "description": "Optional request metadata.",
+  "properties": {},
+  "type": "object"
+}
    • changedInput schema / properties / prompt / description
      Previous value: -"User prompt text."New value: +"Convenience shortcut for one user text message; do not combine with messages."
    • addedInput schema / properties / service_tier
      Added value: +{
+  "description": "Optional service-tier hint.",
+  "type": "string"
+}
    • addedInput schema / properties / stop_sequences
      Added value: +{
+  "description": "Optional stop sequences.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / temperature
      Added value: +{
+  "description": "Optional sampling temperature.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}
    • addedInput schema / properties / thinking
      Added value: +{
+  "additionalProperties": {},
+  "description": "Thinking configuration for compatible models.",
+  "properties": {},
+  "type": "object"
+}
    • addedInput schema / properties / tool_choice
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    }
+  ],
+  "description": "Tool choice policy or explicit tool selection."
+}
    • addedInput schema / properties / tools
      Added value: +{
+  "description": "Native Anthropic tool definitions.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / top_k
      Added value: +{
+  "description": "Optional top-k sampling cutoff.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / top_p
      Added value: +{
+  "description": "Optional nucleus sampling probability.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}
    • changedInput schema / required
      Previous value: -[
-  "model",
-  "prompt"
-]New value: +[
+  "model"
+]
  6. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the bar is lower. The description earns credit by adding auth requirements ('x-api-key' or 'Authorization: Bearer') and capability notes (vision, streaming) that the annotations do not convey.

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?

Three tight sentences with the purpose front-loaded, then capabilities, then auth. No filler, no repetition of the name.

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

Completeness3/5

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

No output schema exists, yet the description says nothing about return shape, streaming response behavior, or the non-standard X-TokenLab-Delivery-Policy parameter. For a 15-parameter generation tool this leaves real gaps an agent would want covered.

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?

With 15 parameters at 73% schema description coverage, the schema does most of the documentation work. The description adds nothing parameter-specific beyond noting model/vision support, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource ('Creates a model response using Anthropic's native request format'), which implicitly separates it from format-specific siblings like create_gemini_content or create_chat_completion. However, it never names an alternative, so the agent must infer the routing rather than read it.

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

Usage Guidelines3/5

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

It notes Claude model support with vision and streaming, and specifies the auth headers to use, which implies the usage context. But it gives no explicit when-to-use/when-not guidance or comparison to the other create_* completion siblings, leaving selection to inference.

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

Deploy Server

Other Tools