Skip to main content
Glama
BlockRunAI

BlockRun MCP

Official
by BlockRunAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

blockrun_chat

Send a message to any AI model to get a second opinion, or route tasks to specialized models by mode: coding, reasoning, cheap, or free.

Instructions

Get a second opinion from another AI model, or use a specialized model for a specific task.

Notable modes:

  • mode:"powerful" → Claude Opus 5, Claude Opus 4.8, GPT-5.6-sol, Claude Fable 5 (frontier, 1M context)

  • mode:"reasoning" → Claude Opus 5, GPT-5.6-sol, Kimi K3, Grok 4.3, deepseek-v4-pro

  • mode:"coding" → Claude Opus 5, GPT-5.3-codex, Kimi K3, Grok Build, GLM-5.2

  • mode:"cheap" → deepseek-v4-pro, Qwen3.7 Flash, MiniMax M3, Tencent Hy3

  • mode:"glm" → Zhipu GLM-5 / 5.2 / 5.1 / 5-Turbo (strong at coding)

  • mode:"free" → free models (no cost)

Pick directly: model:"anthropic/claude-opus-5.5", model:"openai/gpt-6-sol", model:"xai/grok-4.7", model:"moonshot/kimi-k3", model:"nvidia/gpt-oss-120b" (free).

Run blockrun_models to see all available models with pricing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoRouting mode: powerful/reasoning = frontier models (Opus 5, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (great for coding), cheap = budget models, free = $0 models (ignored if model specified)
stopNoUp to 4 stop sequences; generation halts when any is produced
modelNoSpecific model ID (e.g., 'openai/gpt-6-sol', 'anthropic/claude-sonnet-5.5', 'zai/glm-5')
systemNoOptional system prompt
messageYesYour message to the AI
agent_idNoAgent identifier. If a budget was delegated for this agent_id via blockrun_wallet action:'delegate', spending is tracked and enforced. The agent is hard-stopped when its budget is exhausted.
messagesNoConversation history for multi-turn context. When provided, 'message' is appended as the final user turn. Use with explicit 'model' param (defaults to 'openai/gpt-5.6-terra' if not specified). Note: if you include a role:'system' entry in messages[], do not also pass the system param to avoid duplicate system messages.
thinkingNoAnthropic extended thinking. Only honored for anthropic/claude-* models — these go direct to the native /v1/messages endpoint and the response includes verbatim type:'thinking' blocks with their original signature. Ignored for non-Claude models (no native thinking channel).
max_tokensNoMax tokens in response
temperatureNoCreativity 0-2
response_formatNoSet to 'json_object' to force valid JSON output (no markdown fences). Works across all providers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.54.1
    • changedInput schema / properties / model / description
      Previous value: -"Specific model ID (e.g., 'moonshot/kimi-k3', 'openai/gpt-5.6-sol', 'zai/glm-5')"New value: +"Specific model ID (e.g., 'openai/gpt-6-sol', 'anthropic/claude-sonnet-5.5', 'zai/glm-5')"
  2. Changed1 schema field changedv0.49.0
    • changedInput schema / properties / mode / description
      Previous value: -"Routing mode: powerful/reasoning = frontier models (Opus 5, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (great for coding), cheap = budget models, free = NVIDIA only (ignored if model specified)"New value: +"Routing mode: powerful/reasoning = frontier models (Opus 5, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (great for coding), cheap = budget models, free = $0 models (ignored if model specified)"
  3. Changed1 schema field changedv0.45.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  4. Changed1 schema field changedv0.40.1
    • changedInput schema / properties / mode / description
      Previous value: -"Routing mode: powerful/reasoning = frontier models (Opus 4.8, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (cheap, great for coding), cheap = budget models, free = NVIDIA only (ignored if model specified)"New value: +"Routing mode: powerful/reasoning = frontier models (Opus 5, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (great for coding), cheap = budget models, free = NVIDIA only (ignored if model specified)"
  5. Changed3 schema fields changedv0.33.0
    • changedInput schema / properties / messages / description
      Previous value: -"Conversation history for multi-turn context. When provided, 'message' is appended as the final user turn. Use with explicit 'model' param (defaults to 'openai/gpt-5.5' if not specified). Note: if you include a role:'system' entry in messages[], do not also pass the system param to avoid duplicate system messages."New value: +"Conversation history for multi-turn context. When provided, 'message' is appended as the final user turn. Use with explicit 'model' param (defaults to 'openai/gpt-5.6-terra' if not specified). Note: if you include a role:'system' entry in messages[], do not also pass the system param to avoid duplicate system messages."
    • changedInput schema / properties / mode / description
      Previous value: -"Routing mode: glm = Zhipu GLM-5/GLM-5-Turbo ($0.001/call, great for coding), coding = GLM-5 + code models, cheap = GLM-5 + budget, free = NVIDIA only (ignored if model specified)"New value: +"Routing mode: powerful/reasoning = frontier models (Opus 4.8, GPT-5.6-sol, Kimi K3), coding = code-specialized, glm = Zhipu GLM (cheap, great for coding), cheap = budget models, free = NVIDIA only (ignored if model specified)"
    • changedInput schema / properties / model / description
      Previous value: -"Specific model ID (e.g., 'zai/glm-5', 'openai/o3')"New value: +"Specific model ID (e.g., 'moonshot/kimi-k3', 'openai/gpt-5.6-sol', 'zai/glm-5')"
  6. Changed2 schema fields changedv0.31.6
    • removedInput schema / properties / routing
      Removed value: -{
-  "description": "Set to \"smart\" to auto-select the optimal model via ClawRouter (14-dimension AI routing)",
-  "enum": [
-    "smart"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / routing_profile
      Removed value: -{
-  "default": "auto",
-  "description": "Cost/quality profile for ClawRouter: \"eco\" (budget), \"auto\" (balanced, default), \"premium\" (best quality). Note: \"free\" maps to \"auto\" (the SDK dropped the free profile) and still settles a PAID model — for zero-cost generation use mode:\"free\" or model:\"nvidia/...\". Only applies when routing:\"smart\".",
-  "enum": [
-    "free",
-    "eco",
-    "auto",
-    "premium"
-  ],
-  "type": "string"
-}
  7. Changed5 schema fields changedv0.25.2
    • changedInput schema / properties / routing_profile / description
      Previous value: -"Cost/quality profile for ClawRouter: \"free\" (zero cost NVIDIA), \"eco\" (budget), \"auto\" (balanced, default), \"premium\" (best quality) (only applies when routing: \"smart\")"New value: +"Cost/quality profile for ClawRouter: \"eco\" (budget), \"auto\" (balanced, default), \"premium\" (best quality). Note: \"free\" maps to \"auto\" (the SDK dropped the free profile) and still settles a PAID model — for zero-cost generation use mode:\"free\" or model:\"nvidia/...\". Only applies when routing:\"smart\"."
    • changedInput schema / properties / thinking / properties / budget_tokens / description
      Previous value: -"Tokens Claude may spend reasoning before answering. max_tokens is auto-raised above this if needed."New value: +"Tokens Claude may spend reasoning before answering (1024–100000; Anthropic requires ≥1024). max_tokens is auto-raised above this if needed; counts toward the budget reserve."
    • addedInput schema / properties / thinking / properties / budget_tokens / maximum
      Added value: +100000
    • changedInput schema / properties / thinking / properties / budget_tokens / minimum
      Previous value: -1New value: +1024
    • changedInput schema / properties / thinking / properties / budget_tokens / type
      Previous value: -"number"New value: +"integer"
  8. Changed7 schema fields changedv0.22.0
    • changedInput schema / properties / messages / description
      Previous value: -"Conversation history for multi-turn context. When provided, 'message' is appended as the final user turn. Use with explicit 'model' param (defaults to 'openai/gpt-5.4' if not specified). Note: if you include a role:'system' entry in messages[], do not also pass the system param to avoid duplicate system messages."New value: +"Conversation history for multi-turn context. When provided, 'message' is appended as the final user turn. Use with explicit 'model' param (defaults to 'openai/gpt-5.5' if not specified). Note: if you include a role:'system' entry in messages[], do not also pass the system param to avoid duplicate system messages."
    • addedInput schema / properties / messages / items / properties / content / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "anyOf": [
+        {
+          "properties": {
+            "text": {
+              "type": "string"
+            },
+            "type": {
+              "const": "text",
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "text"
+          ],
+          "type": "object"
+        },
+        {
+          "properties": {
+            "image_url": {
+              "properties": {
+                "url": {
+                  "description": "https URL or data:<mime>;base64,<...> URI",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "url"
+              ],
+              "type": "object"
+            },
+            "type": {
+              "const": "image_url",
+              "type": "string"
+            }
+          },
+          "required": [
+            "type",
+            "image_url"
+          ],
+          "type": "object"
+        }
+      ]
+    },
+    "type": "array"
+  }
+]
    • addedInput schema / properties / messages / items / properties / content / description
      Added value: +"Plain text, or an array of parts for multimodal input (text + image_url). Images are honored on the native anthropic/claude-* path."
    • removedInput schema / properties / messages / items / properties / content / type
      Removed value: -"string"
    • addedInput schema / properties / response_format
      Added value: +{
+  "description": "Set to 'json_object' to force valid JSON output (no markdown fences). Works across all providers.",
+  "enum": [
+    "text",
+    "json_object"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / stop
      Added value: +{
+  "description": "Up to 4 stop sequences; generation halts when any is produced",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 4,
+  "type": "array"
+}
    • addedInput schema / properties / thinking
      Added value: +{
+  "description": "Anthropic extended thinking. Only honored for anthropic/claude-* models — these go direct to the native /v1/messages endpoint and the response includes verbatim type:'thinking' blocks with their original signature. Ignored for non-Claude models (no native thinking channel).",
+  "properties": {
+    "budget_tokens": {
+      "description": "Tokens Claude may spend reasoning before answering. max_tokens is auto-raised above this if needed.",
+      "minimum": 1,
+      "type": "number"
+    },
+    "type": {
+      "const": "enabled",
+      "type": "string"
+    }
+  },
+  "required": [
+    "type",
+    "budget_tokens"
+  ],
+  "type": "object"
+}
  9. First observedv0.16.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only assert readOnlyHint=false/destructiveHint=false/openWorldHint=false, which says little about cost or model-specific behavior. The description adds genuinely useful context: 'free → free models (no cost)', which modes map to which model families, and that specific model IDs can be picked directly. It still doesn't disclose that this consumes paid budget per call, so it falls short of full transparency.

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 is front-loaded, then a scannable bulleted mode list, then direct model-ID examples and a pointer to blockrun_models. The list is long but each bullet carries a distinct routing fact; the repeated model names across modes are mildly redundant but not wasteful enough to penalize heavily.

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?

For an 11-parameter tool with nested objects and no output schema, the description covers only mode/model routing. It says nothing about the message-vs-messages relationship, the thinking/temperature/response_format/stop controls, or what the response looks like. The schema carries that load, so the description is adequate but not complete for a tool of this complexity.

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 description coverage is 100%, so the baseline would be 3. The description goes beyond that by expanding the `mode` enum into concrete model rosters per mode and giving example `model` IDs, which helps an agent choose values rather than just read an enum list. It adds nothing for the other nine parameters.

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?

The opening sentence gives a clear verb+resource ('Get a second opinion from another AI model, or use a specialized model for a specific task') and the mode bullets make it unambiguous that this is a chat/completion router. It implicitly distinguishes itself from the media siblings (blockrun_video, blockrun_image, blockrun_speech) by being text-model-oriented, but it never names a sibling to contrast against.

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?

Strong routing guidance: each mode is annotated with what it is good for ('coding = code-specialized', 'glm = Zhipu GLM (great for coding)', 'cheap = budget models'), and it explicitly points to blockrun_models for discovery. It lacks any when-not guidance (e.g., when to use messages[] instead of a single message, or when a different sibling tool is the right call).

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