Reach MCP — LinkedIn for AI agents

list_page_activity

Read-onlyIdempotent

List a company page's activity, as in the page admin's Activity tab, newest first: comments on the page's posts, mentions, reshares, visitor digests. Each item has card_type (COMMENT, MENTION, PAGE_ACTIVITY_NEW_VISITORS…), the line LinkedIn shows, read, and for a comment its comment_urn, comment_text, the post (post_urn, post_text) and who acted: actor_name, actor_type (member or company) and actor_linkedin_id or actor_company_id. Pass comment_urn to reply_comment or like_post with the same page_id to answer as the page. Paged with start/next_start. Use to see what happened on a company page (who commented, mentioned or reshared) and find comments to answer; then reply_comment or like_post with comment_urn and the same page_id. Reading does not mark the cards seen. One LinkedIn call per page. Read-only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "account_id": "<account_id>",
      "page_id": "<page_id>"
    },
    "name": "list_page_activity"
  }
}

Input Schema

Name	Required	Description
`count`	No	Page size.
`start`	No	Pagination offset, 0-based.
`page_id`	Yes	The company page (page_id or vanity name from list_managed_pages); needs read_activity.
`account_id`	Yes	Reach id of the LinkedIn account to act on, from list_accounts.
`card_types`	No	Only these card types (e.g. ['COMMENT']); filters the page LinkedIn returns.

Output Schema

Name	Required	Description
`items`	No
`next_start`	No	Pass as start for the next page
`unseen_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 5, 2026
- addedOutput schema / properties / items / items / properties / actor_company_id
```
Added value: +{
+  "description": "Company id when a page acted",
+  "type": "string"
+}
```
- changedOutput schema / properties / items / items / properties / actor_linkedin_id / description
```
Previous value: -"fsd_profile id of who acted"New value: +"fsd_profile id of who acted (a member)"
```
- addedOutput schema / properties / items / items / properties / actor_name
```
Added value: +{
+  "description": "Name of who acted",
+  "type": "string"
+}
```
- addedOutput schema / properties / items / items / properties / actor_type
```
Added value: +{
+  "description": "member or company",
+  "type": "string"
+}
```
AddedNov 3, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds non-obvious behavior on top: results are newest-first, 'Reading does not mark the cards seen' (a real side-effect an agent would otherwise assume), and 'One LinkedIn call per page' (a cost/rate signal). This is exactly the kind of context annotations cannot convey.

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 with purpose, then item shape, then chaining, then pagination/caveats — a sensible order with no filler. It loses a point for mild redundancy: the comment_urn + same page_id handoff to reply_comment/like_post is stated twice in slightly different words, and the long field enumeration sentence is dense.

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

Completeness5/5

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

For a five-parameter, read-only listing tool with an output schema and full annotation coverage, the description supplies everything needed: what comes back, ordering, filtering by card type, pagination, side-effect behavior, cost, and the downstream reply flow. Nothing an agent needs in order to call this correctly is missing.

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 coverage is 100%, so baseline is 3, but the description goes further by giving concrete card_type values (COMMENT, MENTION, PAGE_ACTIVITY_NEW_VISITORS) where the schema has no enum, and by tying page_id to 'the same page_id' used in reply_comment/like_post. Pagination is described as 'start/next_start', which clarifies usage beyond the bare integer offset in the schema.

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?

Opens with a specific verb+resource ('List a company page's activity') and anchors it to a concrete mental model ('the page admin's Activity tab'), then enumerates what counts as activity: comments, mentions, reshares, visitor digests. This clearly separates it from siblings like list_page_posts (content authored by the page) and list_notifications (personal notifications).

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?

Both when-to-use ('see what happened on a company page... and find comments to answer') and what to do next ('then reply_comment or like_post with comment_urn and the same page_id') are stated explicitly, with the required chaining parameter named. The page_id dependency on list_managed_pages is covered in the schema, and the guidance names the concrete follow-on tools rather than leaving alternatives implicit.

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

All Reach MCP — LinkedIn for AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?