Skip to main content
Glama
yutori-ai

Yutori MCP

Official
by yutori-ai
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

run_research_task

Execute a deep web research task that searches, reads, and synthesizes information from across the web. Returns a task ID to poll for results.

Instructions

Execute a one-time deep web research task. The research agent searches, reads, and synthesizes information from across the web. Returns a task_id for polling. Example: 'latest AI startup funding announcements'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
webhook_urlNo
output_fieldsNo
user_locationNo
user_timezoneNo
webhook_formatNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

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

  1. Changed23 schema fields changedv0.3.1
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / description
      Removed value: -"Input for running a one-time research task.\n\nThe Research API executes deep web research on any topic.\nAn AI agent searches, reads, and synthesizes information from across the web.\nExamples:\n- Research competitive landscape for a product\n- Summarize recent news about a company\n- Find technical documentation or specifications"
    • addedInput schema / properties / output_fields / anyOf
      Added value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / output_fields / description
      Removed value: -"Optional: Extract structured data as an array of objects with these field names. Example: ['title', 'summary', 'source_url']. If omitted, returns human-readable text. For complex schemas, call the Yutori REST API directly (see example at: https://docs.yutori.com/reference/research-create#using-webhooks-and-a-structured-output-schema)."
    • removedInput schema / properties / output_fields / items
      Removed value: -{
-  "type": "string"
-}
    • removedInput schema / properties / output_fields / minItems
      Removed value: -1
    • removedInput schema / properties / output_fields / type
      Removed value: -"array"
    • removedInput schema / properties / query / description
      Removed value: -"Natural language description of what to research. Examples: 'What are the latest developments in quantum computing from the past week?', 'Research the competitive landscape for AI code assistants', 'Find pricing information for cloud GPU providers'"
    • addedInput schema / properties / user_location / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / user_location / description
      Removed value: -"Location for contextual awareness. Format: 'city, region, country'. Default: 'San Francisco, CA, US'"
    • removedInput schema / properties / user_location / type
      Removed value: -"string"
    • addedInput schema / properties / user_timezone / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / user_timezone / description
      Removed value: -"Timezone for contextual awareness. Example: 'America/New_York'. Default: 'America/Los_Angeles'"
    • removedInput schema / properties / user_timezone / type
      Removed value: -"string"
    • addedInput schema / properties / webhook_format / anyOf
      Added value: +[
+  {
+    "enum": [
+      "scout",
+      "slack",
+      "zapier"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / webhook_format / description
      Removed value: -"Webhook payload format: 'scout' (default), 'slack', or 'zapier'"
    • removedInput schema / properties / webhook_format / enum
      Removed value: -[
-  "scout",
-  "slack",
-  "zapier"
-]
    • removedInput schema / properties / webhook_format / type
      Removed value: -"string"
    • addedInput schema / properties / webhook_url / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / webhook_url / description
      Removed value: -"HTTPS URL to receive webhook notification when research completes. Must use https://."
    • removedInput schema / properties / webhook_url / type
      Removed value: -"string"
    • changedInput schema / title
      Previous value: -"ResearchTaskInput"New value: +"run_research_taskArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "run_research_taskOutput",
+  "type": "object"
+}
  2. Changed2 schema fields changedv0.3.0
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / output_fields / minItems
      Added value: +1
  3. First observedv0.2.9

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description must fully disclose behavior. It mentions async polling ('Returns a task_id for polling') and broad actions (search, read, synthesize), but omits authentication needs, rate limits, data privacy, error handling, or whether it is read-only. The behavior is partially described but insufficiently transparent.

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?

The description is concise: two sentences and an example, with no filler. It front-loads the key action and async nature. While it could include more detail, the structure is efficient and immediately clear.

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

Completeness2/5

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

Given 6 parameters, zero schema descriptions, and an existing output schema, the description is incomplete. It does not elaborate on output format, webhook usage, or parameter effects. The description is minimal and relies heavily on the tool name and sibling context, missing many details needed for correct invocation.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate. It only implicitly references the query parameter via the example and does not explain webhook_url, output_fields, user_location, user_timezone, or webhook_format. No parameter names or purposes are mentioned, leaving agents to infer meaning from context.

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 'Execute a one-time deep web research task' with a specific verb and resource. It differentiates from sibling tools like create_scout (recurring) and run_browsing_task by emphasizing 'one-time' and 'deep web.' The example provides concrete usage context.

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?

The description implies usage for one-time web research via phrases like 'one-time' and 'deep web research,' but it does not explicitly state when to use this tool versus alternatives (e.g., run_browsing_task or create_scout). No when-not or exclusion criteria are provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/yutori-ai/yutori-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server