Skip to main content
Glama

linkedin_unipile_network

Read-only

Your LinkedIn network: 1st-degree connections and invitations. Inviting, answering or withdrawing an invitation is linkedin_unipile_act.

op:

  • "relations" (default): your 1st-degree connections — to target/export your direct network. Paginated (cursor). Returns {items, cursor, …} — a single list. fields = PROJECTION: keeps only those fields on each item (e.g. ["name","headline","public_identifier","created_at"]), plus member_id always kept — reduces an export's payload. A key that no connection on the page carries is REFUSED, with the keys present. ⚠️ Pagination is NOT reliable for an EXHAUSTIVE export: the cursor encodes a volatile offset (duplicates in the offset space, overestimated total) and a limit=100 page returns 90-100 items, not 100. To load a whole network: deduplicate by member_id (NEVER the offset), keep ≤6 pages in parallel, ~20 s between two salvos (measured: 8 in parallel → 429 "We only allow 10 requests" on 3 of them; beyond that, cascading 502s), prove exhaustion with 2 staggered passes. ⚠️ These six precautions are ALL there is to know: they live here, there is no page to go read. The bulk-load guide deals with something else — delegating a big load to a sub-agent — and says nothing about the pagination traps above. ⚠️ An incomplete load does NOT RAISE, it returns fewer people: a process that reads the absence as "not a connection" will then act on a wrong answer.

  • "invitations": the connection invitations. direction='received' (received, to accept) or 'sent' (sent, pending). Paginated — limit (default 50, MAX 100: beyond that upstream returns "Invalid querystring"; and with no limit the whole backlog exceeds the token limit). For the next page, pass the cursor RETURNED by the previous call — and only that: a hand-made cursor is refused. No more returned cursor = end of the backlog (a SHORT page is not the end), unless pagination_note is present: it then says why pagination stopped there, and there is nothing more to ask for. direction is repeated on each page, it cannot be deduced from the cursor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "linkedin_unipile_network"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNorelations (default) | invitations.relations
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
limitNopage size.
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
cursorNopagination (relations, invitations) — always the one returned by the previous call, never built by hand.
fieldsNoop="relations" — field projection (`member_id` always kept; key absent from the whole page = refusal).
_run_idNoOBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
_accountNoCompte à OPÉRER quand plusieurs existent. `oto_identity(op='list')`.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
directionNoop="invitations" — 'received' (default) or 'sent'.received

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true, and the description does not contradict that. It adds substantial behavior the agent could not otherwise know: cursor encodes a volatile offset, limit=100 yields 90-100 items, 429 'We only allow 10 requests' beyond a threshold with cascading 502s, and crucially that an incomplete load returns fewer rows rather than raising — a silent wrong-answer risk.

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?

Well structured with per-`op` bullets and warnings placed ahead of the detail, and every operational sentence carries information. Some meta-commentary is expendable — 'These six precautions are ALL there is to know… there is no page to go read' and the aside about the `bulk-load` guide are defensive noise rather than tool facts.

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 an 11-parameter, no-output-schema pagination tool, it covers the things that actually break calls: pagination termination rules, `pagination_note`, short-page caveat, limits, and rate-limit spacing. Return shape is only lightly sketched ('{items, cursor, …}') and infra params are left entirely to the schema, but nothing essential to calling 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 baseline is 3; the description still adds real meaning: `fields` keeps member_id always and refuses a key absent from the whole page, `cursor` must be the one returned by the previous call (hand-made cursors refused), limit max 100, and `direction` is repeated per page and cannot be deduced from the cursor. The six cross-cutting infra params (_org, _group, _run_id, _account, _project, _instance) are never touched in the description, which keeps it off a 5.

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 precise verb+resource statement ('Your LinkedIn network: 1st-degree connections and invitations') and immediately names the sibling that handles the write side ('Inviting, answering or withdrawing an invitation is `linkedin_unipile_act`'). The two `op` modes are then spelled out, so an agent can choose 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 Guidelines5/5

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

Explicit routing: 'relations' for targeting/exporting the direct network, 'invitations' with direction='received' (to accept) or 'sent' (pending), and mutation routed to `linkedin_unipile_act`. It even prescribes the operational procedure for an exhaustive export (dedup by member_id, ≤6 pages in parallel, ~20 s spacing, two staggered passes to prove exhaustion).

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