LinkedIn Intelligence MCP Server (southleft/linkedin-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 87 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
56/100

LinkedIn Intelligence MCP Server

Connects Claude Desktop to LinkedIn's data layer for AI-powered networking, enabling profile research, content creation and scheduling, engagement automation, analytics tracking, and messaging through natural language.

→ southleft/linkedin-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

southleft

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: LINKEDIN_PASSWORD, THIRDPARTY_RAPIDAPI_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes87 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

debug_context

Debug tool to check the internal state of the MCP server.

get_my_profile

Get the authenticated user's LinkedIn profile.

get_profile

Get comprehensive LinkedIn profile data with multi-source enrichment.

get_profile_contact_info

Get contact information for a LinkedIn profile.

get_profile_skills

Get skills and endorsements for a LinkedIn profile.

get_profile_interests

Get profile interests including influencers, companies, groups, and topics.

get_similar_profiles

Get profiles similar to a given profile.

get_profile_articles

Get articles written by a LinkedIn profile.

get_article

Get the full content of a LinkedIn article.

get_company_by_domain

Get company information by website domain.

get_network_stats

Get statistics about the authenticated user's LinkedIn network.

batch_get_profiles

Get multiple LinkedIn profiles efficiently.

get_cache_stats

Get cache statistics and performance metrics.

get_feed

Get the authenticated user's LinkedIn feed.

get_profile_posts

Get posts from a specific LinkedIn profile.

create_post

Create a new LinkedIn post using the Official API (recommended) or unofficial API.

create_image_post

Create a LinkedIn post with an image using the Official API.

create_video_post

Create a LinkedIn post with a video using the Official API.

create_document_post

Create a LinkedIn post with a document (PDF, PPTX, DOCX) using the Official API.

create_poll

Create a LinkedIn poll using the Official API.

delete_post

Delete a LinkedIn post using the Official API.

edit_post

Edit/update an existing LinkedIn post using the Official API.

create_comment

Create a comment on a LinkedIn post using the Official API.

delete_comment

Delete a comment from a LinkedIn post using the Official API.

get_comments_official

Get comments on a LinkedIn post using the Official API.

create_reaction

Add a reaction to a LinkedIn post or comment using the Official API.

delete_reaction

Remove a reaction from a LinkedIn post or comment using the Official API.

get_auth_status

Get LinkedIn authentication status for both official and unofficial APIs.

search_ads

Search for ads in the LinkedIn Ad Library.

search_ads_by_advertiser

Search for all ads by a specific advertiser/company.

search_ads_by_keyword

Search for ads containing a specific keyword.

analyze_draft_content

Analyze draft content and get suggestions for improvement.

create_draft

Create a content draft for later publishing.

list_drafts

List all content drafts.

get_draft

Get a specific draft by ID.

update_draft

Update a content draft.

delete_draft

Delete a content draft.

publish_draft

Publish a draft as a LinkedIn post.

schedule_post

Schedule a post for future publishing.

list_scheduled_posts

List all scheduled posts.

get_scheduled_post

Get a specific scheduled post.

cancel_scheduled_post

Cancel a scheduled post.

update_scheduled_post

Update a scheduled post.

get_post_reactions

Get reactions/likes on a specific post.

get_post_comments

Get comments on a specific post.

search_people

Search for people on LinkedIn.

search_companies

Search for companies on LinkedIn.

search_content

Search LinkedIn for posts and content by keyword.

search_jobs

Search for job postings on LinkedIn.

get_job

Get detailed information about a specific job posting.

get_job_skills

Get skills required for a job posting.

get_profile_views

Get profile view statistics for the authenticated user.

get_conversations

Get your LinkedIn messaging conversations.

get_conversation

Get messages for a specific conversation.

get_conversation_details

Get conversation ID and details for a specific profile.

send_message

Send a LinkedIn message to one or more recipients. Optionally attach an image.

reply_to_conversation

Reply to an existing LinkedIn conversation. Optionally attach an image.

mark_conversation_as_seen

Mark a conversation as read/seen.

get_invitations

Get pending connection invitations you've received.

send_connection_request

Send a connection request to a LinkedIn profile.

reply_invitation

Accept or reject a connection invitation.

remove_connection

Remove an existing LinkedIn connection.

get_company

Get detailed company information.

get_company_updates

Get recent posts/updates from a company page.

get_organization_followers

Get follower count for an organization using the Community Management API.

get_school

Get school/university information.

get_post_analytics

Get analytics for a specific post.

get_rate_limit_status

Get current rate limit status.

analyze_engagement

Perform deep engagement analysis on a specific post.

analyze_content_performance

Analyze content performance patterns for a profile.

analyze_optimal_posting_times

Analyze optimal posting times based on engagement patterns.

analyze_post_audience

Analyze the audience engaging with a specific post.

analyze_hashtag_performance

Analyze hashtag usage and performance.

generate_engagement_report

Generate a comprehensive engagement report for a profile.

get_my_posts

Get your own LinkedIn posts.

get_my_post_analytics

Get analytics for your own posts using the Official API.

analyze_my_content_performance

Analyze your content performance comprehensively.

get_my_posting_recommendations

Get personalized posting recommendations based on your content performance.

generate_my_content_calendar

Generate a content calendar based on your performance data.

get_profile_sections

Get all editable profile sections with current content.

get_profile_completeness

Calculate profile completeness score with improvement suggestions.

update_profile_headline

Update profile headline.

update_profile_summary

Update profile summary/about section.

upload_profile_photo

Upload a new profile photo.

upload_background_photo

Upload a new background/banner photo.

add_profile_skill

Add a skill to your profile.

check_browser_automation_status

Check if browser automation is available for profile updates.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configLINKEDIN_API_ENABLED"": "true",
configLINKEDIN_EMAIL
🔐 secretLINKEDIN_PASSWORD
🔐 secretTHIRDPARTY_RAPIDAPI_KEYyour_api_key
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

87/87 tools missing one or more hints — debug_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_my_profile (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_profile (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +84 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

4 tools perform destructive updates without destructiveHint — create_image_post deletes at line 1188 (os.unlink(temp_file.name)); create_video_post deletes at line 1307 (os.unlink(temp_file.name)); create_document_post deletes at line 1434 (os.unlink(temp_file.name))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool inputs are validated

77/87 tool handlers declare input schemas (89%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

67/87 tool handlers wrap calls in try/catch (77%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/southleft/linkedin-mcp?variant=verified)](https://m8ven.ai/mcp/southleft/linkedin-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 843a48f1261dfd9df30f195be7b1128451d4cc5a
code hash: a87f57eec70548fe83718087856fcaa6774065725602ff42ad5bd715872d5a11
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client