LinkedIn MCP Zero
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LINKEDIN_MCP_ENABLE_PATCHRIGHT_FALLBACK | No | Set to 'true' to enable opt-in Patchright fallback when CDP is unavailable. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_jobsC | Search LinkedIn jobs by keyword/location. |
| search_jobs_multiC | Search multiple public job boards. |
| get_job_detailsC | Get full public LinkedIn job details. |
| get_company_jobsC | Get public jobs for a company. |
| get_company_profileC | Get public company profile signals. |
| search_companiesC | Search companies from public job signals. |
| get_job_salaryB | Extract salary from public job details. |
| get_job_trendsC | Get hiring trends by role/location. |
| get_industry_insightsD | Get public market insights for an industry. |
| search_jobs_advancedD | Advanced public LinkedIn job search. |
| analyze_resumeC | Parse resume PDF/DOCX/text locally. |
| get_resume_insightsC | Get local resume skill gaps and suggestions. |
| match_jobs_to_resumeC | Rank public jobs against a saved resume. |
| compare_jobsC | Compare 2-5 public LinkedIn jobs. |
| export_jobsC | Export public job details to a local file. |
| save_job_alertC | Save a recurring job search. |
| get_saved_alertsB | List saved job alerts. |
| check_saved_alertsC | Run saved alerts and report new matches. |
| get_my_profileA | Get your LinkedIn profile via CDP browser. |
| get_person_profileC | Get a person's LinkedIn profile via CDP browser. |
| search_peopleC | Search people via CDP browser. |
| get_my_connectionsC | Get your LinkedIn connections via CDP browser. |
| get_inboxC | Get recent LinkedIn conversations via CDP browser. |
| get_conversationC | Read a LinkedIn conversation via CDP browser. |
| get_feedC | Get LinkedIn home feed via CDP browser. |
| get_notificationsC | Get LinkedIn notifications via CDP browser. |
| get_sidebar_profilesB | Get sidebar profile suggestions via CDP browser. |
| get_company_employeesC | Get company employees via CDP browser. |
| check_sessionA | Check CDP browser and LinkedIn session readiness. |
| get_engine_statusC | Show available engines. |
| get_helpC | Show tool documentation. |
| get_profile_voyagerC | Get a profile through gated Voyager mode. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 32 tools
Many tools have distinct purposes, but some overlap exists, e.g., multiple search tools (search_jobs, search_jobs_advanced, search_jobs_multi) and profile retrieval tools (get_person_profile, get_profile_voyager). This could cause confusion for agents.
All tools follow a consistent verb_noun pattern (e.g., analyze_resume, get_company_profile, search_jobs). This makes the set predictable and easy to navigate.
At 32 tools, the set is slightly large but still manageable. Some fine-grained tools (e.g., get_job_salary separate from get_job_details) feel slightly redundant but overall justified for the domain's complexity.
The server covers major LinkedIn operations: job search, company info, people profiles, resume analysis, messaging, and notifications. Minor gaps like posting or endorsements exist, but core workflows are well-supported.