# Welcome to the Jungle MCP connector Connect Welcome to the Jungle to Elaichi and Claude, ChatGPT, Cursor or any MCP client can list jobs, update candidates, add comments and log emails, each person working inside their own access with every call logged. Source: https://elaichi.ai/connectors/welcometothejungle/ ## Facts | | | | --- | --- | | Application | Welcome to the Jungle | | Category | ATS | | AI tools | 27 | | Authentication | Connects with an API key | | Bring your own OAuth app | No | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead | ## What you can ask once Welcome to the Jungle is connected - List open jobs in the Paris office with no candidates yet - Add a comment to Maria Lopez's candidate record with my screening notes - Update the Senior Designer job title to Lead Designer ## Connect Welcome to the Jungle in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Welcome to the Jungle. 2. Optionally set Share with, then press Connect. 3. Paste a Welcome to the Jungle API key. One person generates a token in Welcome to the Jungle and pastes it once. Everyone else works through Share with, and never sees it. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Welcome to the Jungle tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Welcome to the Jungle MCP connector for Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Welcome to the Jungle MCP connector for ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Welcome to the Jungle MCP connector for Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Welcome to the Jungle to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Welcome to the Jungle tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Welcome to the Jungle through Elaichi ### Catch a candidate up after a screening call Recruiting. Update the candidate's record in Welcome to the Jungle and add a comment with your notes while the call is still fresh. The next recruiter who opens the profile sees exactly where things stand. ### See every open job in one list Hiring managers. Ask for all open jobs in your department or office and get the live list from Welcome to the Jungle, without logging in to check each one. ### Open a new job from the chat Talent acquisition. Describe the role, pick the department and office, and the job is created in Welcome to the Jungle ready for review. ### Fix titles across many jobs at once People operations. When a leveling change renames ten roles, update the jobs in Welcome to the Jungle in one bulk change instead of editing them one by one. ### Keep departments and offices current HR. When a new office opens or a team splits, create or update the department and office in Welcome to the Jungle so new jobs land in the right place. ### Log the email and attach the CV Recruiting coordinators. Record the email you sent a candidate and attach their updated CV to the Welcome to the Jungle profile so the whole history lives in one place. ## Elaichi vs Zapier MCP vs Composio for Welcome to the Jungle All three can connect Welcome to the Jungle to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay. | What to check | Elaichi | Zapier MCP | Composio | | --- | --- | --- | --- | | Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. | | Control over Welcome to the Jungle tools | Allow or restrict single Welcome to the Jungle tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. | | Record of calls | One audit entry per Welcome to the Jungle call. | A History tab of tool calls. | A log of every tool call. | | Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. | | Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. | Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026. Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/). ## Frequently asked questions ### How do I connect Welcome to the Jungle to Claude? Connect Welcome to the Jungle in Elaichi first, then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Welcome to the Jungle connects with an API key, so you paste the key from your Welcome to the Jungle account into Elaichi and that is the whole sign-in step. There is no OAuth application to register and no client ID or secret to generate. ### Does Welcome to the Jungle work with ChatGPT and Cursor as well as Claude? Yes. Once Welcome to the Jungle is connected in Elaichi it is available to Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent through the same endpoint, https://api.elaichi.ai/mcp. You connect it once and every client picks it up. ### What can an AI agent actually do with my Welcome to the Jungle data? An agent can list your open Welcome to the Jungle jobs, open a candidate's record, update it after a call, add a comment, log an email and attach a CV. It can also create a new job, change several jobs at once, and keep departments and offices current as the company grows. Short concrete asks, such as "update the Lyon designer job title", work better than long sentences. ### Does connecting Welcome to the Jungle give the AI access to everything in my account? No. Every call runs under the Welcome to the Jungle account that was connected, so the agent only sees the jobs, candidates, departments and offices that account can already see. Elaichi can narrow that access further for each team and never widens it beyond what the account holds. ### Can my team share one Welcome to the Jungle connection? Yes. One person connects Welcome to the Jungle in Elaichi and shares the connection with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so the audit log names the person behind every change to a job or candidate. ### Can I stop an agent from deleting or changing things in Welcome to the Jungle? Yes. In Elaichi you restrict each Welcome to the Jungle action on its own, for example allowing reading candidates and jobs but blocking updates and new records. A restricted action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can reach it. ### What happens to a Welcome to the Jungle connection when someone leaves? When someone is offboarded in Elaichi, their access to Welcome to the Jungle through every client ends at once. A Welcome to the Jungle connection shared with the team keeps working for everyone else. If you want to remove the connector entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client. ### Does the Welcome to the Jungle MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Welcome to the Jungle is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs. ### Is Elaichi an alternative to Zapier MCP for Welcome to the Jungle? Yes. Both let Claude, ChatGPT or Cursor use Welcome to the Jungle. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Welcome to the Jungle call. ### How is Elaichi different from Composio for Welcome to the Jungle? Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Welcome to the Jungle: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call. ## All 27 Welcome to the Jungle tools Every tool below is callable through https://api.elaichi.ai/mcp once Welcome to the Jungle is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Welcome to the Jungle jobs** (List). List jobs for a given organization in Welcome to the Jungle. Returns each job's reference, name, status, contract_type, language, description, profile, salary, office_id, and created_at/updated_at/published_at/archived_at timestamps. Optional: organization_reference (defaults to the connected organization). Default page size 100 (maximum not documented by the vendor). - **Get single Welcome to the Jungle job by ID** (Get). Get a single Welcome to the Jungle job by id (its reference). Returns the job's reference, name, status, contract_type, language, description, profile, salary, office_id, and created_at/updated_at/published_at/archived_at timestamps; boolean query flags can additionally include stages, candidates_count, websites, application_fields, and organization. Required: id. - **Create a Welcome to the Jungle job** (Create). Create a job in Welcome to the Jungle. Returns the created job, including its reference, status, and created_at/updated_at timestamps. Required: name, description, profile, contract_type, language (plus at least one office attribute: office_id, office_address, office_zip_code, office_city, office_country_code, or offices). Optional: organization_reference (defaults to the connected organization). - **Update a Welcome to the Jungle job by ID** (Update). Update a Welcome to the Jungle job record by id (its reference). Returns the updated job's reference, name, status, contract_type, language, description, profile, salary, office_id, and created_at/updated_at/published_at/archived_at timestamps. Required: id. To change a job's status use jobs.bulk_update (update_status). - **Welcome to the Jungle jobs bulk update** (Update). Update the status of a Welcome to the Jungle job (draft, published, or archived). Returns the updated job's reference, name, status, contract_type, language, description, profile, salary, office_id, and created_at/updated_at/published_at/archived_at timestamps. Required: job_reference and status. - **List all Welcome to the Jungle job dependencies** (List). Get the reference value lists used by welcometothejungle job fields (e.g. valid values for contract_type, education_level, experience_level, remote, salary, and cms_sites_references). Returns a list holding one object with: contract_types, education_levels, experience_levels, remote_levels, salary_currencies, salary_periods, cms_sites_references. - **List all Welcome to the Jungle languages** (List). List all active languages in Welcome to the Jungle. A language is required when creating a job; this endpoint returns every active language so you can pick one. Returns an array of language objects, each with a human-readable name and a reference code to use as the job's language (e.g. name "English", reference "en"). Returns: name, reference. - **List all Welcome to the Jungle candidates** (List). List Welcome to the Jungle candidates for a given job. Returns an array of candidate records, each with reference, job_reference, stage_id, resume_url, portfolio_url, profile (email, firstname, lastname, phone), origin, archived, created_at, and updated_at. Required: job_reference. - **Get single Welcome to the Jungle candidate by ID** (Get). Get a single Welcome to the Jungle candidate by id (the candidate reference). Returns: reference, cover_letter, created_at, job_reference, modal_path, portfolio_size, portfolio_url, resume_content_type, resume_size, resume_url, stage_id, stage, updated_at, profile, tags, origin, archived. Pass the stage or tags flags to also include the related job stage and tags. Required: id. - **Create a Welcome to the Jungle candidate** (Create). Create a new candidate in Welcome to the Jungle for a given job. Returns the created candidate. Required: job_reference, email, firstname, lastname. Optional: phone, subtitle, tag_list, comment, referrer, social profile URLs. The vendor marks job_stage_id required (string) but its curl omits it; unverified, kept optional. Optional: organization_reference (defaults to the connected organization). - **Update a Welcome to the Jungle candidate by ID** (Update). Update a Welcome to the Jungle candidate by id (the candidate reference); use job_stage_id to move the candidate to another stage or archived to archive them. Returns the updated candidate record including reference, job_reference, stage_id, resume_url, profile, origin, archived, and updated_at. Required: id. - **List all Welcome to the Jungle departments** (List). List Welcome to the Jungle departments (teams) for an organization, used to organize job offers on careers websites. Returns: id, name, is_active, slug, description. Optional: organization_reference (defaults to the connected organization). - **Get single Welcome to the Jungle department by ID** (Get). Get a single Welcome to the Jungle department by id. Returns: id, name, is_active, slug, description. Required: id. - **Create a Welcome to the Jungle department** (Create). Create a department for an organization in Welcome to the Jungle. Returns the created department: id, name, slug, is_active, description. Required: name. Optional: organization_reference (defaults to the connected organization). Per the vendor docs, the slug is automatically generated from the department's name. - **Update a Welcome to the Jungle department by ID** (Update). Update a Welcome to the Jungle department by id. Returns the updated department: id, name, slug, is_active, description. Required: id. - **List all Welcome to the Jungle offices** (List). List all offices of a Welcome to the Jungle organization. Returns: id, name, address, zip_code, city, country_code, is_headquarter. Optional: organization_reference (defaults to the connected organization). - **Get single Welcome to the Jungle office by ID** (Get). Get a single Welcome to the Jungle office by id. Returns: id, name, address, zip_code, city, country_code, is_headquarter. Required: id. - **Create a Welcome to the Jungle office** (Create). Create a new office for a Welcome to the Jungle organization. Returns the created office: id, name, address, zip_code, city, country_code, is_headquarter. Required: name, city, country_code. Optional: organization_reference (defaults to the connected organization). - **Update a Welcome to the Jungle office by ID** (Update). Update an existing Welcome to the Jungle office by id. Returns the updated office: id, name, address, zip_code, city, country_code, is_headquarter. Required: id. - **Create a Welcome to the Jungle comment** (Create). Create a comment for a candidate in Welcome to the Jungle. The comment content accepts plain text, HTML, or markdown. Returns: id, content, raw_content. Required: candidate_reference. - **List all Welcome to the Jungle emails** (List). List Welcome to the Jungle emails for a given candidate. Returns each email's id, subject, body, from_email, to, created_at, origin, candidate_reference, and attachments. Required: candidate_reference. - **Create a Welcome to the Jungle email** (Create). Create an email for a candidate in Welcome to the Jungle. Returns the created email's id, subject, body, from_email, to, created_at, origin, candidate_reference, and attachments. Required: candidate_reference, subject, body, from_email, to. send_email true makes Welcome Kit email the candidate (archived docs: default false). - **List all Welcome to the Jungle attachments** (List). List all documents attached to a candidate in Welcome to the Jungle. Returns: id, job_reference, candidate_reference, filename, file_url, size, content_type, created_at. Required: candidate_reference. Default page size 100 (maximum not documented by the vendor). - **Create a Welcome to the Jungle attachment** (Create). Attach one or more documents to a candidate in Welcome to the Jungle by providing remote file URLs. Returns the created document records including id, job_reference, candidate_reference, filename, file_url, size, content_type, and created_at. Required: candidate_reference and remote_file_urls (array of objects each with filename and url). - **List all Welcome to the Jungle moves** (List). List candidate pipeline moves in Welcome to the Jungle, where a candidate moves between job stages, between jobs, or between organizations. Returns: candidate, from, to, created_at, updated_at. Optional: organization_reference (defaults to the connected organization). Default page size 100 (maximum not documented by the vendor). A job stage is not included if it was deleted after the move. - **List all Welcome to the Jungle me** (List). Get information about the current Welcome to the Jungle user. Returns: avatar_url, display_name. The organizations, jobs and stages query flags add related data, but the vendor does not document its shape (the response schema covers only avatar_url and display_name). - **Get single Welcome to the Jungle organization by ID** (Get). Get information about a Welcome to the Jungle organization by id (its organization reference). Returns: reference, name, slug, description, updated_at, offices, websites. Required: id. The response schema is partial. Offices and websites are only returned when their query flag is true; images and videos have no documented response shape.