Career Agent Workbench MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAREER_AGENT_WORKBENCH_WORKSPACE | No | Path to the private workspace directory. Optional for public-only tool startup, but required for full functionality. | |
| CAREER_AGENT_WORKBENCH_PRIVATE_ENV_FILE | No | Path to the private .env file containing secrets and optional overrides. Optional for public-only tool startup, but required for full functionality. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_linkedin_jobsC | Search bounded guest-accessible public LinkedIn job data. |
| get_linkedin_job_detailsB | Get normalized details for one public LinkedIn job. |
| get_linkedin_job_raw_payloadC | Get one bounded in-memory public LinkedIn detail payload. |
| find_matching_linkedin_jobsD | Run configured local matching over public LinkedIn job data. |
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 4 tools
Search and find_matching both return job listings but serve distinct purposes: ad-hoc searching vs. preconfigured matching. The two get tools are clearly differentiated by normalized vs. raw payload.
All tool names use snake_case with a verb prefix and include 'linkedin_job(s)' as the core noun. Minor variation like 'matching' as a modifier and 'details'/'raw_payload' suffixes does not break the overall pattern.
Four tools is well within the ideal range for a focused job-search server. Each tool serves a clear purpose without redundancy.
The server covers the complete read-only workflow: search to discover jobs, retrieve normalized details, access raw payload for debugging, and run configured matching. No dead ends exist for this domain.