linkedin-mcp-server is a local MCP server that gives compatible AI assistants access to LinkedIn through a logged-in browser session. Agents can use it to inspect profiles and companies, search jobs, retrieve job details, and manage certain LinkedIn interactions. The catalogue add-ons operate this server and expose its LinkedIn workflows to agents.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add stickerdaniel/linkedin-mcp-server --skill linkedin-mcpgit clone --depth 1 https://github.com/stickerdaniel/linkedin-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stickerdaniel/linkedin-mcp-server/linkedin-mcp)<a href="https://agentmods.dev/skills/stickerdaniel/linkedin-mcp-server/linkedin-mcp"><img src="https://agentmods.dev/badge/skills/stickerdaniel/linkedin-mcp-server/linkedin-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stickerdaniel/linkedin-mcp-server/linkedin-mcp"><img src="https://agentmods.dev/badge/skills/stickerdaniel/linkedin-mcp-server/linkedin-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00564 |
| Opus 5 | $0.00022 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
linkedin-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn MCP
Use the bundled linkedin MCP server only when the user explicitly asks for
LinkedIn data or an action on LinkedIn. Do not call LinkedIn tools for unrelated
work, health checks, or background maintenance.
Operating rules
- Start with the smallest read operation that can answer the request.
- Treat profile, company, job, post, feed, and message results as live LinkedIn evidence. Distinguish retrieved facts from inference.
- Keep searches and result pages modest. Do not bulk scrape or spam.
- Never enable the plugin or its MCP server, edit Codex configuration, or start a login flow merely because LinkedIn might be useful. If either component is disabled, explain that state and stop.
send_messageandconnect_with_personare write actions. Use them only when the user explicitly authorizes the exact recipient and action. Confirm the final message or connection note unless the user has already supplied it.- Do not retry a failed write action unless the result proves it was not sent.
Browser and authentication
The server uses a managed Chromium browser and the user's own LinkedIn session. Installing or enabling the plugin does not sign in. The first LinkedIn data request may prepare the browser, import an existing local session, or require a visible login window. If LinkedIn presents a captcha, two-factor prompt, or other user-owned authentication step, stop and ask the user to complete it.
If browser setup or authentication is still in progress, report that exact state and retry once after it finishes. Do not loop, launch extra browser instances, clear profiles, or replace the user's browser session.
Tool selection
- Profiles:
get_my_profile,get_person_profile,search_people, andget_sidebar_profiles. - Companies:
get_company_profile,get_company_posts,search_companies, andget_company_employees. - Jobs:
search_jobs,get_saved_jobs, andget_job_details. - Content:
get_feedandsearch_posts. - Messages:
get_inbox,get_conversation, andsearch_conversations. - Writes:
send_messageandconnect_with_person, subject to the explicit authorization rules above. - Cleanup: use
close_sessiononly when the user asks to end the managed browser session or when the current LinkedIn task is finished and no follow-up call is expected.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 52 lines · 43 tokens per session scan A e6f966f53bc0
linkedin-mcp is a skill published in the GitHub repository stickerdaniel/linkedin-mcp-server (3,384 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 564 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.
dream
Consolidate and reorganize project memory (MEMORY.md) by invoking the dream-consolidator named subagent (Sonnet, pinned via the agent's model: frontmatter — NEVER pass a model: parameter yourself, it defeats the pin and runs the dream on expensive Opus). The subagent prompt is a CLOSED TEMPLATE: send its fields and…
project-memory
Maintain persistent project memory in MEMORY.md via MCP tools. SCOPE: codebase/architecture/conventions/gotchas + Recent Sessions of code work, in /MEMORY.md. DISTINCT from Claude Code's auto memory (/.claude/projects/ /memory/, holds user profile/preferences/feedback). Code-about → here; user-about → auto memory.…
tool-description-check
Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing or source, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field…