Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

linkedin_unipile_act

Destructive

⚠️ ACTS on LinkedIn from the person's own account — the other members see it, at once, with no draft: a message, a post, a comment, a reaction, an invitation, an endorsement. Reading is linkedin_unipile (messaging), linkedin_unipile_post, linkedin_unipile_network, linkedin_unipile_profile.

op — messaging (DM):

  • "send" (default): sends text. chat_id → replies in an existing thread; otherwise recipient_id (the recipient's provider id) → opens a new thread.

  • "react_message": reacts to a MESSAGE with a native emoji (reaction, e.g. '👍') — the counterpart sees it. message_id = id of a message from linkedin_unipile(op="read"); chat_id is required on the v2 API, ignored in v1.

  • "update": changes a thread's state — action ∈ setReadStatus | setMuteStatus | setArchiveStatus | setPinnedStatus | setLabel | getInviteLink; value = boolean for the statuses, string for setLabel, omitted for getInviteLink. ⚠️ setReadStatus can show the counterpart that you read them.

op — posts, published publicly in the person's name:

  • "publish_post": publishes a post (text).

  • "comment_post": comments on a post (post_id, text).

  • "react_post": reacts to a POST (post_id) — value: LIKE (default) | PRAISE | EMPATHY | INTEREST | APPRECIATION | ENTERTAINMENT. post_id = social_id (urn:li:…) from linkedin_unipile_post or linkedin_unipile_profile(op="posts").

op — invitations:

  • "invite": sends a connection request. provider_id = the provider_id of a linkedin_unipile_search / linkedin_unipile_profile result; message = note ≤300 characters.

  • "accept_invitation" / "decline_invitation": answers a RECEIVED invitation — invitation_id AND shared_secret from the SAME item of linkedin_unipile_network(op="invitations", direction="received").

  • "cancel_invitation": withdraws a SENT invitation (invitation_id of a direction="sent" item).

op — a member (identifier = public slug or URN):

  • "endorse": endorses a skill (skill_endorsement_id = endorsement_id of a skill from linkedin_unipile_profile(op="person")).

  • "update_member": premium action — api = 'sales_navigator' (action 'saveLead', optional list_id) or 'recruiter' (action 'addCandidateToPipeline' | 'addApplicantToPipeline' | 'changeCandidatePipeline' | 'rejectApplicant', hiring_project_id, stage 'UNCONTACTED' | 'CONTACTED' | 'REPLIED').

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_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNosee above (default "send").send
apiNoop="update_member" — 'sales_navigator' or 'recruiter'.
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
textNosend / publish_post / comment_post — the content.
stageNoop="update_member" — recruiter pipeline stage.
valueNoop="update" — value of the thread action; op="react_post" — the reaction type (default LIKE).
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
actionNoop="update" — the thread action; op="update_member" — the premium action.
_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.
chat_idNothread id (send-in-a-thread, update, react_message v2).
list_idNoop="update_member" — target Sales Navigator list (saveLead).
messageNoop="invite" — accompanying note (≤300 characters).
post_idNocomment_post / react_post — the post's social_id.
_accountNoCompte à OPÉRER quand plusieurs existent. `oto_identity(op='list')`.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
reactionNoop="react_message" — the emoji.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
identifierNoendorse / update_member — the member.
message_idNoop="react_message" — id of the targeted message.
provider_idNoop="invite" — recipient's LinkedIn provider id.
recipient_idNoop="send" — recipient's provider id (new thread).
invitation_idNoaccept_invitation / decline_invitation / cancel_invitation.
shared_secretNoaccept_invitation / decline_invitation — LinkedIn token of the same item (required).
hiring_project_idNoop="update_member" — recruiter pipeline actions.
skill_endorsement_idNoop="endorse" — id of the skill to endorse.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the destructive/openWorld annotations, it discloses that actions are instant with no draft and visible to other members, warns that setReadStatus can reveal a read receipt, notes the v2 requirement that chat_id be supplied for react_message, and flags update_member as a premium action. It does not cover failure modes, invitation/rate limits, or what a successful call returns, which keeps it short of a 5.

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 warning about public, immediate action is front-loaded before any parameter detail, and the op-group headings make a long description scannable. It is dense and long, but for a 25-parameter multiplexer nearly every line carries a constraint or identifier provenance that would otherwise be lost.

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 destructive, open-world mutation tool with no output schema and no required parameters, the description covers all twelve ops, their inputs, and their identifier sources — enough for correct invocation. It stops short of describing return values, partial-failure behavior, or account/org targeting, which an agent would have to infer from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is a 3, but the description adds genuine meaning: it maps parameters to each op, states cross-parameter dependencies (chat_id required on v2 and ignored on v1; shared_secret must come from the same invitation item), gives the reaction-type enumeration with LIKE default, and specifies the ≤300 character note limit. Infrastructure params (_org, _run_id, etc.) are left to their already-explicit schema descriptions.

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?

The opening line states a specific verb and scope — 'ACTS on LinkedIn from the person's own account' — and immediately distinguishes it from the read-only siblings (linkedin_unipile, linkedin_unipile_post, linkedin_unipile_network, linkedin_unipile_profile). The per-op breakdown makes clear exactly which actions the tool performs.

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?

It explicitly routes reading to other tools and then gives when-to-use context for each op group (messaging, posts, invitations, member), including where each required identifier must come from (e.g. invitation_id AND shared_secret from the SAME direction="received" item; post_id as social_id from linkedin_unipile_post). Little is left to inference.

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

All Tulina 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