Skip to main content
Glama

List Recent LinkedIn Conversations

li_list_conversations
Read-only

List one account's most recent LinkedIn message threads, read live from LinkedIn in a browser session on the worker (it queues behind other browser work, so it can take a while). Each row has the other participant (participantName, participantProfileUrl, participantProfileId = their ACoAA… member id), lastActivityAt, unreadCount, the latest message text (lastMessageText), weOweReply (true when THEY spoke last), addressable (false for sponsored/InMail blasts, which carry no participant identity and cannot be replied to) and, when we track that person, ours (our status, outcome, campaign). It sends nothing and changes no contact, message or conversation record (the read only notes the account's own member id, so threads between your own accounts can be recognised).

FILTERS. onlyNeedsReply=true keeps threads where they spoke last; onlyAddressable=true drops the blasts; sinceDays and profileUrl narrow further. The walk pages by cursor until limit threads pass THOSE filters, the inbox ends, or a page ceiling is hit. With onlyNeedsReply the server then ALSO drops, and counts: threads somebody already decided about after their last message — handled, completed, outcome-marked or snoozed (alreadyDecidedCount; a newer message from them brings the thread back flagged reopened); threads with your own team's accounts (excludedInternalCount); LinkedIn itself — blasts and "The LinkedIn Team" (excludedSystemCount); and threads reviewed with li_mark_reviewed and unchanged since (alreadyReviewedCount). Those drops happen AFTER limit, so a page can hold fewer rows than asked. A lookup that fails filters NOTHING and says so (decidedLookupFailed, internalLookupFailed, reviewLookupFailed). Somebody we hold no record for is untracked, not decided, and stays listed until a mark records them (li_mark_outcome / li_mark_reply_handled / li_snooze_reply accept the participantProfileUrl and create a light record).

COVERAGE. Check reachedEnd and truncated before concluding anyone is absent: a walk that stopped early has not seen older threads. participantProfileId is the member id li_send_bulk_messages takes for its fast path. Pair with li_read_conversation for a full thread. Seen status is NOT here (it would cost one extra call per thread); stored reads carry it — see li_conversation_history (seenByThemAt).

Input Schema

NameRequiredDescriptionDefault
limitNoHow many threads to collect (default 20, max 200), counted after onlyNeedsReply / onlyAddressable / sinceDays / profileUrl but BEFORE the decided / internal / system / reviewed drops, so the reply can hold fewer. The inbox is walked by cursor, 20 threads per round trip, until this many match, the inbox runs out or the page ceiling is hit — a large number costs browser time. Check `reachedEnd`.
sessionIdNoAccount id from li_list_accounts. Omit (with sessionLabel) to use your default account.
sinceDaysNoOnly threads active in the last N days. Check `truncated` and `reachedEnd`: the walk stops at the page ceiling or your `limit`, so a window reaching past `coversSince` is NOT answered here — raise `limit`, or name the people and use li_read_conversations_bulk.
profileUrlNoOnly the thread with this person (vanity /in/<slug> or ACoAA… URL)
sessionLabelNoAccount by label, LinkedIn name, profile slug or member id (li_list_accounts). Omit (with sessionId) to use your default account.
onlyNeedsReplyNoReturn only threads where the other person spoke last (we owe a reply)
onlyAddressableNoDrop threads that cannot be replied to — LinkedIn sponsored/InMail blasts, with or without a named sender, which still count as "they spoke last". Off by default so nothing is hidden; the response always reports how many were unaddressable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / onlyAddressable / description
      Previous value: -"Drop threads with no identifiable participant — LinkedIn sponsored/InMail blasts, which still count as \"they spoke last\" but cannot be replied to. Off by default so nothing is hidden; the response always reports how many were unaddressable."New value: +"Drop threads that cannot be replied to — LinkedIn sponsored/InMail blasts, with or without a named sender, which still count as \"they spoke last\". Off by default so nothing is hidden; the response always reports how many were unaddressable."
  2. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"How many to return AFTER filtering (default 20). The inbox is walked by cursor, 20 threads per round trip, until this many MATCH or the inbox runs out — so a large number with onlyNeedsReply is honest but costs browser time. Check `reachedEnd`."New value: +"How many threads to collect (default 20, max 200), counted after onlyNeedsReply / onlyAddressable / sinceDays / profileUrl but BEFORE the decided / internal / system / reviewed drops, so the reply can hold fewer. The inbox is walked by cursor, 20 threads per round trip, until this many match, the inbox runs out or the page ceiling is hit — a large number costs browser time. Check `reachedEnd`."
  3. Changed2 schema fields changed
    • changedInput schema / properties / sessionId / description
      Previous value: -"Optional saved LinkedIn session selector"New value: +"Account id from li_list_accounts. Omit (with sessionLabel) to use your default account."
    • changedInput schema / properties / sessionLabel / description
      Previous value: -"Optional saved LinkedIn session selector"New value: +"Account by label, LinkedIn name, profile slug or member id (li_list_accounts). Omit (with sessionId) to use your default account."
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, yet the description adds substantial behavior: it queues behind browser work and can be slow, sends nothing and changes no record, notes the account's own member id, drops rows AFTER limit (so a page can hold fewer than requested), and reports lookup-failure flags rather than silently filtering. This is far beyond what annotations 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?

It is long, but well-structured with front-loaded purpose and clear FILTERS / COVERAGE sections, and the density is largely justified because there is no output schema to carry the field and count semantics. A few clauses about count flags could be tightened, but almost every sentence earns its place.

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?

With no output schema, the description carries the full burden of explaining returns — participantName/participantProfileUrl/participantProfileId, lastActivityAt, unreadCount, lastMessageText, weOweReply, addressable, ours, and the alreadyDecidedCount/excludedInternalCount/excludedSystemCount/alreadyReviewedCount counters — plus coverage caveats (reachedEnd, truncated). Nothing an agent needs to call or interpret it 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 the baseline is 3, but the description adds genuine semantics: the interplay of onlyNeedsReply/onlyAddressable/sinceDays/profileUrl, the fact that filtering counts happen before the decided/internal/system/reviewed drops, and that participantProfileId is the member id li_send_bulk_messages consumes. It goes beyond restating 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+scope: 'List one account's most recent LinkedIn message threads, read live from LinkedIn in a browser session.' It immediately differentiates from siblings by naming li_read_conversation for a full thread and li_conversation_history for stored reads, so an agent can route without opening another 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?

Explicitly states when to use each filter (onlyNeedsReply keeps threads where they spoke last; onlyAddressable drops blasts) and names alternatives with their triggering conditions (li_read_conversations_bulk for named people, li_mark_outcome/li_mark_reply_handled/li_snooze_reply for untracked senders). It even warns which filters do NOT answer a query.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources