Skip to main content
Glama

LinkMCP: hosted LinkedIn MCP server

by io.linkmcp
OverviewDiscussionsAdmin

List Conversations

linkedin_list_conversations
Read-onlyIdempotent

List your LinkedIn DM conversations (inbox). Returns conversation ID, timestamp, unread status, the other participant's provider ID, and the LinkedIn thread ID. Each conversation includes the other person's name, and their headline and profile link when LinkedIn provides them, so no profile lookup is needed to see who a conversation is with. Supports cursor-based pagination. Optionally search for conversations with a specific person by providing a participant identifier. Results come in pages: when has_more is true, more conversations exist; call again with the same arguments and cursor set to next_cursor.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
afterNoOnly return conversations updated after this time (exclusive). ISO 8601 date or datetime, for example 2026-08-15 or 2026-08-15T09:30:00Z. A date or time without an offset is read as UTC.
limitNoNumber of conversations to return per page (1–250, default 20). Ignored when participant is provided.
beforeNoOnly return conversations updated before this time (exclusive). ISO 8601 date or datetime, for example 2026-08-15 or 2026-08-15T09:30:00Z. A date or time without an offset is read as UTC.
cursorNoPagination cursor from a previous response. Omit for the first page.
participantNoFind conversations with a specific person. Provide a LinkedIn profile URL, public ID, URN, or numeric ID. Each call scans only your most recent conversations to find matching threads. Other filters (unread_only, after, before) still apply. Use cursor to continue scanning if not found.
unread_onlyNoIf true, return only conversations with unread messages. If false, return only read conversations. Omit to return all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / participant / description
      Previous value: -"Find conversations with a specific person. Provide a LinkedIn profile URL, public ID, URN, or numeric ID. Scans up to 1250 recent conversations to find matching threads. Other filters (unread_only, after, before) still apply. Use cursor to continue scanning if not found."New value: +"Find conversations with a specific person. Provide a LinkedIn profile URL, public ID, URN, or numeric ID. Each call scans only your most recent conversations to find matching threads. Other filters (unread_only, after, before) still apply. Use cursor to continue scanning if not found."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/openWorld, so the description's value-add is disclosure of return fields, page-loop semantics, and the important caveat that participant search 'scans only your most recent conversations.' That scanning limitation is genuine behavioral context not derivable from annotations.

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 first sentence front-loads purpose and the pagination rule comes last, which is the right ordering. The enumerated return fields are slightly verbose but justified because no output schema exists.

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?

Given no output schema, the description compensates by naming the returned fields and explaining the paging loop end-to-end, so an agent can correctly call it repeatedly and interpret results without further documentation.

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 coverage is 100%, so the baseline is 3. The description restates the participant behavior and the has_more/next_cursor contract but adds no format or syntax detail beyond what the schema already documents for each parameter.

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 and resource ('List your LinkedIn DM conversations (inbox)') and immediately scopes it against the message-level sibling by noting the return fields are conversation summaries, not messages. An agent can distinguish it from linkedin_get_conversation_messages without opening the schema.

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?

Gives clear operational guidance: use the participant identifier to find a specific person's thread, and loop with cursor when has_more is true. It does not name the alternative message-retrieval tool explicitly, so routing to a sibling is implied rather than stated.

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

All LinkMCP: hosted LinkedIn MCP server toolsInspect
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