TalentLyft MCP by usefulapi
RemoteAbout TalentLyft MCP by usefulapi
A hosted MCP server for TalentLyft users to read jobs, candidates, applications, stages and interview events, and to add candidate notes or move applications between stages. It uses a TalentLyft access token and needs no local installation.
Key features
- 01List and retrieve jobs and stages
- 02Browse candidates and activities
- 03Inspect applications and pipelines
- 04Review departments, members and events
- 05Add candidate notes or move applications
Use cases
- 01Review job openings and recruitment stages
- 02Look up candidate records and activity
- 03Track applications across pipelines
- 04Record candidate notes or change an application stage
MCP support
Exposes TalentLyft read tools and tools for adding candidate notes and moving applications to MCP clients via a hosted remote endpoint. Users provide a TalentLyft access token when connecting.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://talentlyft.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-talentlyft https://talentlyft.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-talentlyft":{"type":"http","url":"https://talentlyft.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-talentlyft":{"type":"http","url":"https://talentlyft.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-talentlyft":{"type":"http","url":"https://talentlyft.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-talentlyft":{"serverUrl":"https://talentlyft.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMETalentLyft MCP by usefulapi
Use your TalentLyft account from Claude, Cursor, or any MCP client. Reads jobs, candidates, applications, stages and interview events, and adds candidate notes or moves applications to another stage. Hosted, no local install: connect with your own credentials.
Live endpoint: https://talentlyft.usefulapi.io/mcp · Homepage: https://usefulapi.io
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://talentlyft.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http talentlyft https://talentlyft.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"talentlyft": {
"url": "https://talentlyft.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your TalentLyft credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/talentlyft/
On first connect you provide your TalentLyft Access token (profile icon → Integrations → TalentLyft Access token settings). The server validates it and stores it per user. No keys go in config files.
Tools
| Tool | Type | What it does |
|---|---|---|
talentlyft_list_jobs | read | List jobs |
talentlyft_get_job | read | Get a job |
talentlyft_list_job_stages | read | List job stages |
talentlyft_list_candidates | read | List candidates |
talentlyft_get_candidate | read | Get a candidate |
talentlyft_list_candidate_activities | read | List candidate activities |
talentlyft_get_application | read | Get a candidate application |
talentlyft_list_pipelines | read | List pipelines |
talentlyft_list_departments | read | List departments |
talentlyft_list_members | read | List members |
talentlyft_list_rejection_reasons | read | List rejection reasons |
talentlyft_list_events | read | List events |
talentlyft_add_candidate_note | write | Add a note to a candidate |
talentlyft_move_application_to_stage | write | Move an application to a stage |
talentlyft_usage_status | meta | Usage status (free-tier meter) |
talentlyft_request_feature | meta | Request a missing feature |
talentlyft_upgrade | meta | Upgrade to Pro or Pro+ |
talentlyft_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro (per user) | $9/mo or $90/yr (2 months free) | 10,000 tool calls / month |
| Pro+ (per user) | $39/mo or $390/yr (2 months free) | 100,000 tool calls / month |
Each paid plan covers this server only. Ask your AI to run talentlyft_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with talentlyft_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with talentlyft_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.