AIsa Web Search & Research

Get Map Data

post_tavily_map

Destructive

List a site's URLs from a root url without fetching any page content. Steer it with natural-language instructions and regex select_paths / exclude_paths / select_domains filters. Returns base_url and results — a flat array of URL strings, not objects — with response_time and request_id. Fast and cheap: measured at about 1.5 seconds. Use it to size a site before committing to a crawl, then fetch only the parts that matter with post_tavily_extract. When you want the content rather than the shape, post_tavily_crawl does both in one call.

Usage-based billing; Default request estimate: $0.064 USD (not a fixed price). Declared unit rate: $0.008 USD per tavily_credit. Account-specific pricing and final settlement may differ.

Input Schema

Name	Required	Description	Default
`body`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedOct 19, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / allow_external

Removed value: -{
-  "default": true,
-  "description": "Include external domain links in the final results list.",
-  "type": "boolean"
-}

addedInput schema / properties / body

Added value: +{
+  "properties": {
+    "allow_external": {
+      "default": true,
+      "description": "Include external domain links in the final results list.",
+      "type": "boolean"
+    },
+    "exclude_domains": {
+      "description": "Regex patterns to exclude specific domains or subdomains from mapping.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "exclude_paths": {
+      "description": "Regex patterns to exclude URLs with specific path patterns.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "include_usage": {
+      "default": false,
+      "description": "Include credit usage information in the response.",
+      "type": "boolean"
+    },
+    "instructions": {
+      "description": "Natural language instructions for the crawler.",
+      "type": "string"
+    },
+    "limit": {
+      "default": 50,
+      "description": "Total number of links the crawler will process before stopping.",
+      "minimum": 1,
+      "type": "integer"
+    },
+    "max_breadth": {
+      "default": 20,
+      "description": "Max number of links to follow per level of the tree.",
+      "maximum": 500,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "max_depth": {
+      "default": 1,
+      "description": "Max depth of the mapping.",
+      "maximum": 5,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "select_domains": {
+      "description": "Regex patterns to select crawling to specific domains or subdomains.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "select_paths": {
+      "description": "Regex patterns to select only URLs with specific path patterns.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "timeout": {
+      "default": 150,
+      "description": "Maximum time in seconds to wait for the map operation.",
+      "format": "float",
+      "maximum": 150,
+      "minimum": 10,
+      "type": "number"
+    },
+    "url": {
+      "description": "The root URL to begin the mapping.",
+      "example": "docs.tavily.com",
+      "type": "string"
+    }
+  },
+  "required": [
+    "url"
+  ],
+  "type": "object"
+}

removedInput schema / properties / exclude_domains

Removed value: -{
-  "description": "Regex patterns to exclude specific domains or subdomains from mapping.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedInput schema / properties / exclude_paths

Removed value: -{
-  "description": "Regex patterns to exclude URLs with specific path patterns.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedInput schema / properties / include_usage

Removed value: -{
-  "default": false,
-  "description": "Include credit usage information in the response.",
-  "type": "boolean"
-}

removedInput schema / properties / instructions

Removed value: -{
-  "description": "Natural language instructions for the crawler.",
-  "type": "string"
-}

removedInput schema / properties / limit

Removed value: -{
-  "default": 50,
-  "description": "Total number of links the crawler will process before stopping.",
-  "minimum": 1,
-  "type": "integer"
-}

removedInput schema / properties / max_breadth

Removed value: -{
-  "default": 20,
-  "description": "Max number of links to follow per level of the tree.",
-  "maximum": 500,
-  "minimum": 1,
-  "type": "integer"
-}

removedInput schema / properties / max_depth

Removed value: -{
-  "default": 1,
-  "description": "Max depth of the mapping.",
-  "maximum": 5,
-  "minimum": 1,
-  "type": "integer"
-}

removedInput schema / properties / select_domains

Removed value: -{
-  "description": "Regex patterns to select crawling to specific domains or subdomains.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedInput schema / properties / select_paths

Removed value: -{
-  "description": "Regex patterns to select only URLs with specific path patterns.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedInput schema / properties / timeout

Removed value: -{
-  "default": 150,
-  "description": "Maximum time in seconds to wait for the map operation.",
-  "format": "float",
-  "maximum": 150,
-  "minimum": 10,
-  "type": "number"
-}

removedInput schema / properties / url

Removed value: -{
-  "description": "The root URL to begin the mapping.",
-  "example": "docs.tavily.com",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "url"
-]New value: +[
+  "body"
+]

First observedSep 15, 2026

TDQS

A4.1/5.0

Behavior3/5

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

The description adds real behavioral context beyond the annotations: no page content is fetched, ~1.5s latency, and a usage-based cost. However, it never reconciles the annotation profile (readOnlyHint=false, destructiveHint=true) — the text reads as a harmless listing while the annotations warn of a destructive, non-idempotent operation, and the agent gets no guidance on which to trust.

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?

Front-loaded: the core operation and its scope land in the first clause, then filters, return shape, cost/speed, and sibling routing. Dense but every sentence carries information; the only dead weight is the boilerplate pricing block.

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

Completeness4/5

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

An output schema exists, yet the description helpfully pre-empts the biggest return-value pitfall ('a flat array of URL strings, not objects') and names the envelope fields. With that plus sibling routing and latency/cost disclosure, little is missing except guidance reconciling the destructive annotation.

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?

Reported top-level schema coverage is 0% (the `body` wrapper is undocumented), though the nested properties all carry descriptions. The description reinforces the interaction model for `instructions` and the regex filter families (`select_paths`/`exclude_paths`/`select_domains`) but is silent on the cost-controlling knobs (limit, max_depth, max_breadth, timeout, allow_external), which matter for a billed tool.

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?

Specific verb+resource ('List a site's URLs from a root url') with an explicit scope qualifier ('without fetching any page content'), and it names the sibling tools it is not (post_tavily_extract, post_tavily_crawl). An agent can distinguish it from the other ~30 tools without opening a schema.

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

Usage Guidelines5/5

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

Gives an explicit workflow condition: 'Use it to size a site before committing to a crawl, then fetch only the parts that matter with post_tavily_extract', plus the contrasting case 'When you want the content rather than the shape, post_tavily_crawl does both in one call.' When-to-use and alternatives are both stated outright.

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

All AIsa Web Search & Research tools Inspect

Try in Browser

Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?