Nilyo

LinkedIn: Search people

linkedin_search_people

Read-onlyIdempotent

Search LinkedIn Classic people with the user's own LinkedIn account. Use to find a person/provider user ID from a name, title, employer, location, industry, keywords or network distance. When the next requested action is message/invitation, take the chosen result's id and pass it to the action tool; never pass a profile URL directly to an action requiring user_id. Some filters require IDs; resolve them first with linkedin_get_search_parameters.

Input Schema

TableJSON Schema

Name	Required	Description
`cursor`	No
`school`	No
`service`	No
`industry`	No
`keywords`	No
`location`	No	LinkedIn location IDs; call linkedin_get_search_parameters when starting from a human location name.
`account_id`	No	Optional Nilyo connection ID (unipile_account_id from list_connected_accounts). Omit when the user has one account for this provider. When several exist, Nilyo never guesses: list them (display name, identifier, provider user ID), choose the one the user named or ask, and pass its ID here.
`save_search`	No
`followers_of`	No
`past_company`	No
`connections_of`	No
`current_company`	No	LinkedIn company IDs, not company names, when the provider requires IDs.
`network_distance`	No
`profile_language`	No
`advanced_keywords`	No
`save_custom_filter`	No
`open_to_volunteering`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedOct 4, 2026

addedInput schema / properties / advanced_keywords

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "company": {
+      "type": "string"
+    },
+    "first_name": {
+      "type": "string"
+    },
+    "last_name": {
+      "type": "string"
+    },
+    "school": {
+      "type": "string"
+    },
+    "title": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / connections_of
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / followers_of
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / network_distance / items / anyOf

Added value: +[
+  {
+    "const": 1,
+    "type": "number"
+  },
+  {
+    "const": 2,
+    "type": "number"
+  },
+  {
+    "const": 3,
+    "type": "number"
+  }
+]

removedInput schema / properties / network_distance / items / type
```
Removed value: -"string"
```
addedInput schema / properties / open_to_volunteering
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / past_company

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / profile_language

Added value: +{
+  "items": {
+    "maxLength": 2,
+    "minLength": 2,
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / save_custom_filter
```
Added value: +{
+  "not": {}
+}
```
addedInput schema / properties / save_search
```
Added value: +{
+  "not": {}
+}
```

addedInput schema / properties / school

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / service

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

First observedSep 18, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real behavioral context: it operates on the user's own account, some filters require resolved IDs, and result IDs must be forwarded (not URLs) to action tools. It omits pagination behavior despite a cursor parameter, so it is not a full 5.

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, front-loaded with the action and scope, followed by the ID-resolution prerequisite and the downstream hand-off rule. No filler.

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?

For a 17-parameter tool with no output schema, the description covers the critical call-chain (search -> take id -> action tool) and the ID-resolution requirement. It still leaves pagination (cursor) and roughly half the filter parameters unexplained, so it is strong but not fully complete.

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?

Schema description coverage is only 18% across 17 parameters, so the schema does little heavy lifting. The description names several searchable facets (name, title, employer, location, industry, keywords, network distance) and the 'filters require IDs' rule, partially compensating, but leaves cursor, school, service, followers_of, connections_of, network distance encoding, and save_* undocumented.

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+resource and ties it to the correct variant ('LinkedIn Classic people'), which distinguishes it from linkedin_recruiter_search_people and linkedin_sales_navigator_search_people in the sibling list. Also states whose account is used ('the user's own LinkedIn account').

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?

Explicit when-to-use ('find a person/provider user ID from a name, title, employer, location...'), an explicit downstream workflow rule (pass the chosen result's id to the action tool, never a profile URL to a tool requiring user_id), and an explicit prerequisite alternative (resolve filters first with linkedin_get_search_parameters). This is well beyond typical guidance.

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

All Nilyo 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.

LinkedIn: Search people

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources