ashby-jobs
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ashby-jobs what's open at Ramp in engineering?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ashby-jobs
Search and browse any company's public Ashby job board from Claude Code.
Point it at a company's board slug — the {slug} in jobs.ashbyhq.com/{slug} — and it lists open
roles, surfaces the most recently posted ones, and pulls full details for a single posting.
Requirements
Python 3.14+
uv must be on your PATH before you install the plugin. The MCP server is launched as
uv run, so if uv is missing the server fails to start and the tools simply never appear —
check /mcp if the commands are there but nothing works. Python 3.14 and the dependencies are
fetched by uv itself on first launch, which makes that first startup slow.
Related MCP server: JobSpy MCP Server
Install
Add this repo as a plugin marketplace, then install the plugin:
/plugin marketplace add Abhinav-Sriharsha/ashby-jobs-mcp
/plugin install ashby-jobs@ashby-jobsFor local development, point the marketplace at your checkout instead:
/plugin marketplace add /path/to/ashby-mcpThe MCP server starts automatically on install; no manual .mcp.json editing needed.
Commands
Commands are namespaced under the plugin name:
Command | Arguments | Does |
|
| Lists open roles, optionally filtered by title or department |
|
| Shows the most recently posted roles, newest first |
|
| Full details for one posting |
|
| Says whether a company is on Ashby at all, and under which slug |
|
| Tracks a company without looking up its jobs |
| — | Shows every tracked company |
|
| Stops tracking a company |
|
| Saves the default keywords used when searching and iterating |
|
| Sweeps every tracked company for roles posted in the last 24 hours |
/ashby-jobs:latest-jobs ramp Engineering 5
/ashby-jobs:list-jobs ramp backend
/ashby-jobs:job ramp b614563f-3ce6-4dca-b5ba-0e5a6c8bda27
/ashby-jobs:check-company Linear
/ashby-jobs:add-company ramp
/ashby-jobs:set-department engineer, ai, software engineer
/ashby-jobs:iterate-listThe two filters do not work the same way. keyword matches title and department loosely, so
backend works and you can pass a comma-separated list. department on latest-jobs is an exact
match against the board's own department names, so Engineering works but engineer returns
nothing — run list-jobs first if you are not sure what a board calls its departments.
Default department
set-department saves the keywords that list_jobs and iterate_list fall back to when you do not
pass your own. Pass several separated by commas — a job matching any one of them counts. They are
matched against title and department, not against exact department names, so broad terms work on
boards that have no such department: engineer matches OpenAI's Forward Deployed Engineering
roles even though its board has no Engineering department.
/ashby-jobs:set-department engineer, ai, software engineer
/ashby-jobs:list-jobs openai # filtered to those keywords
/ashby-jobs:list-jobs openai all # the whole board anyway
/ashby-jobs:list-jobs openai research # your keyword wins
/ashby-jobs:set-department # clears itKeywords match from a word start, not anywhere in the string. That is what keeps short ones
usable — plain substring matching turns ai into a hit on Retail, Maintenance and Supply
Chain, which is 28 junk results out of 66 on OpenAI's board. The end stays open, so prefixes
still work: engineer matches Engineering and infra matches Infrastructure.
Because a saved default narrows results silently, both tools return keyword_source alongside their
results — default when the saved value applied, argument when yours did, override for all,
and none when nothing filtered.
Tools
The same functions are available to Claude directly, so you can just ask in plain language ("what's open at Ramp in engineering?") instead of using a command.
Tool | Arguments |
|
|
|
|
|
|
|
|
|
|
| — |
|
|
|
|
|
|
list_jobs returns the matching jobs together with the board's live totals:
{
"job_board": "openai",
"total_open_jobs": 734,
"matched_jobs": 383,
"keywords": ["engineer", "ai", "software engineer"],
"keyword_source": "default",
"jobs": [ ... ]
}iterate_list walks every tracked company. A board that fails to fetch is reported in errors
rather than aborting the sweep, so one renamed slug does not cost you the rest of the results.
check_company answers from whether the board exists, not from whether it has postings — Ashby
returns 404 for a slug nobody owns and 200 for a real board even when nothing is open. So a
company with an empty board is still a yes, with open_jobs of 0:
{
"company": "Acme Corp",
"on_ashby": true,
"job_board": "acmecorp",
"board_url": "https://jobs.ashbyhq.com/acmecorp",
"open_jobs": 12,
"tried": ["Acme Corp", "acmecorp"]
}It takes a plain company name as well as a slug: the name is retried as a few normalized slugs
(acmecorp, acme-corp, and legal suffixes dropped), and job_board reports whichever one
resolved, which is the slug the other tools want. tried lists what was attempted, so a false
can be read for what it is — no board found under those names, not proof of absence. When Ashby
cannot be reached, on_ashby is null rather than false, with an error explaining why; a
timeout is not evidence that a company is off Ashby.
Each tool also ships an MCP prompt, available as /mcp__ashby-jobs__<tool_name> — the same
operations, reachable without the plugin's short commands.
Tracked companies
Every company you look up with list_jobs is recorded in a small SQLite database, along with when
it was first and last queried and how many times. add_company adds one up front without fetching
any jobs, list_companies shows them, and remove_company drops one. Names are normalized to
lowercase, so Ramp and ramp are one company.
The tracked list is what iterate_list sweeps. Removing a company only takes it out of that sweep —
you can still look its jobs up directly, and doing so tracks it again.
The database lives at ~/.ashby-mcp/state.db — deliberately outside the plugin directory, so
updating or reinstalling the plugin does not discard it. It also holds the default department set by
set_department. Delete that file to reset both.
Tracking is best-effort inside list_jobs: if the database cannot be written, the job lookup still
returns normally. add_company reports its errors, since recording the company is all it does.
Development
Run the server directly:
uv run ashby-mcpIt speaks MCP over stdio, so nothing may write to stdout except the protocol itself — a stray
print() will corrupt the JSON-RPC stream. Use stderr for debugging output.
Available Tools
9 toolsadd_companyA
Track a company by name without looking up its jobs yet.
Companies are tracked automatically whenever list_jobs runs; this is for adding one ahead of time. Names are matched case-insensitively.
Args: company: the company's slug from jobs.ashbyhq.com/{slug}
Inputs: company (required). Returns: result
check_companyA
Check whether a company hosts its job board on Ashby.
Answers from whether the board exists, not from whether it has postings, so a company that is on Ashby but has nothing open right now still comes back as a yes with open_jobs of 0. on_ashby is null, never false, when Ashby could not be reached.
Args: company: the company's slug from jobs.ashbyhq.com/{slug}, or its plain name. A name is retried as a few normalized slugs, and the one that resolved comes back as job_board for use with the other tools.
Inputs: company (required).
get_jobA
Get full details for one specific job posting, including its description.
Args: job_board_name: the company's slug from jobs.ashbyhq.com/{slug} job_id: the job's id, as returned by list_jobs
Inputs: job_id (required), job_board_name (required).
get_latest_jobsA
Get the most recently posted jobs for a company, optionally filtered to one department.
Args: job_board_name: the company's slug from jobs.ashbyhq.com/{slug} department: optional exact department name to filter to, e.g. "Engineering". Leave blank to include all departments. top_k: how many of the most recent postings to return (default 10)
Inputs: job_board_name (required), top_k, department. Returns: result
iterate_listA
Check every tracked company and return the jobs posted in the last 24 hours.
Args: keyword: optional text to filter by, matched against job title and department (case-insensitive). Accepts several comma-separated keywords and returns jobs matching any of them. Leave blank to use the department saved by set_department, or pass "all" to include every department. hours: how far back to look (default 24)
Inputs: hours, keyword.
list_companiesA
Show every company currently saved in the tracked company list.
These are the boards iterate_list sweeps. A company lands here either from add_company or from any list_jobs lookup.
Inputs: no named parameters.
list_jobsA
List open job postings for a company's public Ashby job board, optionally filtered to titles or departments containing a keyword. Also returns the board's current total number of open postings.
Args: job_board_name: the company's slug from jobs.ashbyhq.com/{slug} keyword: optional text to filter by, matched against job title and department (case-insensitive). Accepts several comma-separated keywords and returns jobs matching any of them. Leave blank to use the department saved by set_department, or pass "all" to list the whole board.
Inputs: job_board_name (required), keyword.
remove_companyB
Remove a company from the tracked company list.
Args: company: the company's slug, matched case-insensitively
Inputs: company (required). Returns: result
set_departmentA
Set the default department or keyword used when searching and iterating.
Accepts several comma-separated keywords, e.g. "engineer, ai, software engineer", and a job matching any one of them counts. Each is matched case-insensitively from a word start in a posting's title or department, so broad terms work on boards that have no department by that name: "engineer" finds "Engineering" roles, while "ai" finds "Applied AI" without dragging in "Retail" or "Maintenance".
Args: department: the keyword or comma-separated keywords to save. Pass an empty string to clear it and go back to searching every department.
Inputs: department. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Most tools are distinct, but list_jobs and get_latest_jobs both return sets of jobs from a single board with overlapping filtering capabilities, so an agent could easily pick the wrong one. iterate_list is distinguishable as a cross-company sweep, and get_job/check_company/company management are clear.
The dominant verb_noun pattern is consistent: list_jobs, get_job, add_company, remove_company, list_companies, set_department. Minor deviations are get_latest_jobs using 'get' instead of 'list' and iterate_list being a less standard verb, but the overall pattern remains predictable.
Nine tools is well-scoped for a job-board-focused server. Each tool maps to a meaningful operation: single-board lookup, detail retrieval, company checking, tracking management, and cross-company iteration.
The server covers the main job-board workflow: check a company, list jobs, get details, track companies, and sweep for recent postings. Minor gaps exist, such as no explicit way to enumerate departments and no update operation for tracked companies, but these are workable limitations rather than dead ends.
Maintenance
Related MCP Connectors
Ashby Jobs Scraper - Search Every Ashby Job Board
Search ~1.4M open jobs from 24k company career boards: Greenhouse, Lever, Ashby, Workday and more
Ashby ATS job scraper pulls live postings via API with team filtering.
Job search across Greenhouse, Lever, Ashby, SmartRecruiters, Workable
Related MCP Servers
- AlicenseAqualityDmaintenanceConnects Claude to the Ashby ATS to manage the hiring pipeline through natural conversation. It enables users to browse jobs, manage candidate profiles, track applications, and coordinate interview stages.245MIT
- AlicenseNot gradedqualityCmaintenanceEnables job search and scraping across multiple job boards (LinkedIn, Indeed, Glassdoor, etc.) with advanced filtering, directly from Claude Desktop or other MCP clients.6MIT
- AlicenseNot gradedqualityDmaintenanceConnects your Ashby recruiting data to Claude, enabling natural language queries and management of candidates, applications, jobs, interviews, offers, and team information.ISC
- AlicenseAqualityBmaintenanceSearch and read public Ashby job boards for named companies, with filtering, full job details, and side-by-side compensation comparison. No API key required.579 npmMIT