Claude MCP Job Assistant
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_jobsC | Fetch jobs using JSearch API and store them temporarily. Return key info. Args: role: The role to search for. location: The location to search for. max_results: The maximum number of jobs to return. Returns: A list of dictionaries containing the job information. |
| save_jobA | Save a specific job from temporary list into candidate's saved folder. If salary not provided, extract it from the fetched job data. Args: job_id: The ID of the job to save. salary (optional): The salary of the job to save. Returns: A string indicating the job was saved successfully. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_job_market | Analyze the job market for top {num_jobs} jobs for '{role}' in '{location}'. |
| personalized_job_recommender | Use the resume to extract key skills, interests, and preferred job types. |
| create_match_report | Given the attached jobs data and resume, create a concise and accurate summary of how well the resume matches the jobs. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| candidate_resume | Extract text from resume.pdf and return as markdown. |
| get_saved_jobs | Return markdown listing of all saved jobs. |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: search_jobs fetches and lists jobs, while save_job persists a specific job. There is no overlap in their functionality, making misselection unlikely.
Both tools follow the verb_noun pattern (search_jobs, save_job) using lowercase snake_case. The consistency is good, though with only two tools there is limited evidence of a broader pattern.
Two tools is quite thin for a job assistant server that presumably requires browsing and managing jobs. Missing operations needed for a complete workflow means the count feels inadequate for the domain.
The surface has notable gaps: there's no way to list or retrieve saved jobs, no delete/discard capability, no detailed view of a job, and no pagination beyond max_results. Agents could reach dead ends when trying to manage or review saved jobs.