instaffo-mcp-server
The instaffo-mcp-server lets an AI assistant access and manage an Instaffo candidate account through a browser session. It can:
Read account information: personal identity, profile details, job suggestions, and conversation history.
Manage job bookmarks: save and unsave job suggestions.
Manage profile details: update 'About me', skills, languages, industries, social links, seniority, and salary expectations (reversible write actions requiring
confirm: true).Manage CV: add, update, and delete work or education entries.
Set skill experience: specify years of experience for skills.
Check authentication status, with optional deep/live validation.
Provide login guidance for establishing a session interactively.
Configure job matching: set target job roles and job-seeking status.
Search skills: look up skill UUIDs in Instaffo's vocabulary.
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., "@instaffo-mcp-server show my job suggestions"
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.
instaffo-mcp-server
An MCP server that gives an AI assistant access to your own Instaffo candidate account, authenticated with your own browser session. Personal job-search tooling. Runs fully local.
Instaffo is a two-sided recruiting marketplace (candidates are matched with companies). This server exposes the candidate side: read your profile and job suggestions, read conversations, and perform reversible write actions, from an MCP client.
How it works
Instaffo has no public candidate API, so the server authenticates with a real
logged-in session. Its candidate web app talks to a clean JSON API under
app.instaffo.com/candidate/api/v1/*, authenticated purely by the session
cookie (no bearer token). So the server is a thin cookie-authenticated httpx
client, not a scraper. A browser (via patchright) is used only once, to mint
the session at login.
MCP client ── stdio ──> instaffo-mcp-server ──cookie──> app.instaffo.com JSON API
│
storage-state.json (cookies, written 0600, git-ignored)
▲
instaffo-mcp --login (one-time browser sign-in)Related MCP server: LinkedIn MCP Server
Setup
uv sync
uv run patchright install chromium # one-time, for login only
uv run instaffo-mcp --login # opens a browser; sign in once
uv run instaffo-mcp --auth-status # confirm the session is storedRegister it with your MCP client (stdio):
{
"command": "uv",
"args": ["run", "--directory", "/path/to/instaffo-mcp-server", "instaffo-mcp"]
}Tools
Reads (no side effects):
Tool | What it returns |
| your identity (name, email, job title) |
| your profile: seniority, location, skills, CV summary |
| your current matches, with counters |
| one role in full: description, requirements, salary, screening questions |
| company requests (inbound interest) and your applications |
| is a session present ( |
| look up skill uuids in Instaffo's closed vocabulary |
Writes (every write tool takes confirm; without it no network call is made
and you get back the exact payload that would be sent):
Tool | Effect | Endpoint |
| bookmark a suggestion |
|
| replace the About me text |
|
| replace the skill set |
|
| replace the language list |
|
| replace industry experience |
|
| replace social links |
|
| set working experience level |
|
| annual salary expectation |
|
| target roles (drives matching) |
|
| active / passive |
|
| add a work or education entry |
|
| edit an entry in place |
|
| remove an entry (irreversible) |
|
| years per skill |
|
All endpoints are observed, never guessed. The contract they were built from is
docs/API.md, dated and derived from a recorded capture.
Why every write reads back
This API returns a bare {"success": true} for every write, and validates
only partially — a PATCH with required fields omitted, or with wrong-typed
values, also returns {"success": true}. The response therefore cannot tell you
what was stored. Each write tool re-reads GET /profile and reports verified
plus value_now; trust those, not the response.
Two field traps worth knowing before you call anything:
instaffo_set_skillsre-derivestopSkillsserver-side. There is notopSkillsfield to send and no UI control for it. A save with the skill set unchanged still moved the top three.Skills cap at 23 (
skills20 +topSkills3). Exceeding it returns"maximum is 20 characters"— the message says characters, the unit is items.
Supervised, on purpose: apply and message
Two actions are intentionally not implemented as fire-and-forget tools: applying to a job, and messaging a recruiter.
Applying is not one request. It is a multi-step wizard that writes lasting self-representations to your real profile before it submits:
a skill self-assessment (year sliders per required skill, e.g. 0-5), which auto-saves to your profile via
experience_durations/bulk_save,your salary expectation (pre-filled from your profile),
an "AI tools you use" and "AI skills" multi-select,
a final submit that creates the application and opens a chat with the recruiter.
Because those are real, outward-facing choices about how you present yourself, and the final submit endpoint only appears once the whole flow is completed, the apply and message tools are left for a supervised session where the account owner approves the inputs. They are not built against a guessed endpoint. The observed sub-steps and wizard shape are recorded here so that session is quick.
Commands
instaffo-mcp # run the MCP server (stdio)
instaffo-mcp --login # headed manual login, persist the session
instaffo-mcp --capture # record app API traffic to a JSONL (diagnostics)
instaffo-mcp --auth-status [--deep]Security and privacy
Session material (
profile/,storage-state.json,captures/,.env) lives under~/.instaffo-mcp, is written0600, and is git-ignored. It is never committed.Write tools are confirm-gated and only touch reversible surfaces.
This is a personal, local tool for your own account. It stores no one else's data and talks only to Instaffo with your own session.
Prior art
The session-capture and browser patterns are adapted in spirit from stickerdaniel/linkedin-mcp-server (Apache-2.0), which authenticates a personal LinkedIn session the same way.
Available Tools
10 toolsinstaffo_auth_statusInstaffo Auth StatusARead-only
Report whether a usable Instaffo session is present.
Inputs: deep. Returns: object
instaffo_get_job_suggestionInstaffo: get one job suggestionARead-only
Full detail for one job suggestion, by its job_uuid (from the list tool).
Includes the role description, requirements, process, salary band, skills, and the screening questions that applying will require answering.
Inputs: job_uuid (required). Returns: object
instaffo_get_profileInstaffo: get my profileARead-only
Return the candidate's Instaffo profile: seniority, location, skills, CV.
Inputs: no named parameters. Returns: object
instaffo_list_conversationsInstaffo: list conversationsARead-only
List chats: company requests (inbound interest) and your job applications.
Inputs: no named parameters. Returns: object
instaffo_list_job_suggestionsInstaffo: list job suggestionsARead-only
List the candidate's current job suggestions (the matches shown in-app).
Inputs: no named parameters. Returns: object
instaffo_loginInstaffo Login InstructionsCRead-only
Explain how to establish a session (interactive, runs in a terminal).
Inputs: no named parameters. Returns: object
instaffo_save_jobInstaffo: save a jobA
Bookmark (favorite) a job suggestion. Reversible with instaffo_unsave_job.
Inputs: job_uuid (required), confirm. Returns: object
instaffo_set_skill_experienceInstaffo: set skill experienceA
Set your years-of-experience for one or more skills on your profile.
This writes to your real profile. Durations are 0-5 (5 means 5+). Only submit truthful values. Without confirm=true it returns a preview.
Inputs: skills (required), confirm. Returns: object
instaffo_unsave_jobInstaffo: unsave a jobA
Remove a job from your bookmarks. Reverses instaffo_save_job.
Inputs: job_uuid (required), confirm. Returns: object
instaffo_whoamiInstaffo: who am IARead-only
Return the signed-in candidate's basic identity.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose, with no overlap between listing, getting details, saving/unsaving jobs, managing profile skills, or authentication.
All tools follow a consistent 'instaffo_verb_noun' pattern, making the action and target clear for each tool.
10 tools cover the core functionalities of a job-seeking assistant (auth, profile, job suggestions, conversations) without being excessive or insufficient.
The set covers most key operations but lacks a tool for applying to jobs, which is a significant gap for automated job search workflows.
Maintenance
Related MCP Connectors
Let AI agents use any website you're logged in to. Sessions stay encrypted on your machine.
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
The career management plugin for your own AI assistant: CVs, cover letters, interviews and more.
LinkedIn jobs, companies and people for AI agents, plus messages and invites via your own account.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to search and apply for jobs on Handshake, track applications, and research employers using your browser session.122MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to read LinkedIn profiles, company pages, jobs, messages, and feed through a user's logged-in browser session.19Apache 2.0
- AlicenseAqualityCmaintenanceEnables AI assistants to access LinkedIn data through the user's logged-in browser session, supporting profiles, companies, job searches, messaging, and feed/posts.21Apache 2.0
- AlicenseAqualityCmaintenanceEnables AI assistants to browse profiles and companies, manage messages and inboxes, and search jobs, posts, and people through a locally logged-in browser session. All actions run on the user's own machine.19Apache 2.0