mcpField
E
Elaichi

Elaichi

VerifiedFeaturedRemote
elaichi.aiData & Analytics0Updated 6d ago

About Elaichi

Elaichi is a governed MCP platform for companies, connecting agents to organizational apps through one endpoint. It applies user permissions, restrictions, and auditing across those connections.

Key features

  1. 01One endpoint for connected company apps
  2. 02Role-based access and restrictions
  3. 03Auditable tool calls
  4. 04Toolboxes and synthetic tools
  5. 05SSO, SCIM, and directory groups

Use cases

  1. 01Let agents act in connected business apps
  2. 02Limit available tools by role
  3. 03Audit agent actions across apps

MCP support

Elaichi exposes connected applications as tools through a remote MCP endpoint. MCP clients connect once to Elaichi, with organizational permissions and restrictions enforced on calls.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.elaichi.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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 README

Elaichi

skills.sh

Elaichi Agent Skills

Official agent skills for Elaichi — the agent platform for companies. Works with Claude Code, Cursor, and any other agent that supports the Agent Skills (SKILL.md) convention.

They do two jobs:

  • Help an agent use Elaichi well — find the right connected tool on the first search, pick the right account, read a refusal correctly, and diagnose a missing tool instead of guessing.
  • Help people find their way around Elaichi — what its words mean, where each screen lives, and how to do a thing, answered inside the AI client they already work in.

Installation

Claude Code

Add this repo as a plugin marketplace, then install the plugin:

/plugin marketplace add trutohq/elaichi-skills
/plugin install elaichi@elaichi-skills

Skills become namespaced as elaichi:elaichi, elaichi:elaichi-mcp, elaichi:elaichi-clients, elaichi:elaichi-connections, elaichi:elaichi-toolboxes, elaichi:elaichi-governance, elaichi:elaichi-automations, elaichi:elaichi-data, elaichi:elaichi-api and elaichi:elaichi-conventions.

The plugin also bundles the Elaichi MCP server, so installing it connects Claude Code to Elaichi too — sign in and choose your organization on the OAuth consent screen when prompted.

To try it locally before installing, run claude --plugin-dir /path/to/elaichi-skills.

Cursor

The plugin listed on the Cursor plugin marketplace is a separate, dedicated repo — trutohq/elaichi-cursor-plugin — not this one. Install Elaichi from there for the marketplace path; it vendors a copy of this repo's skills and rule, kept in sync, alongside the MCP server. This repo (elaichi-skills) is where the skills and the rule are authored, and is what to install directly via npx skills or a remote rule below.

Installing the marketplace plugin also connects the Elaichi MCP server — Cursor will prompt you to sign in and choose your organization on the OAuth consent screen, the same one you'd see connecting any other client.

Before it is listed, or if you'd rather skip the marketplace, add the repo as a remote rule instead: open Cursor Settings → Rules, click Add Rule under Project Rules, choose Remote Rule (GitHub), and enter:

https://github.com/trutohq/elaichi-skills

This pulls in both the skills and the always-applied elaichi rule, but not the MCP server — connect that separately from Customize → MCPs in Cursor.

Any agent (via npx skills)
npx skills add trutohq/elaichi-skills

Add -g to install globally instead of into the current project.

Updating and removing
Claude CodeCursor (marketplace)Cursor (remote rule)npx skills
Update/plugin marketplace update elaichi-skillsManaged by the marketplaceRe-sync the remote rule from Settings → Rulesnpx skills update
Remove/plugin uninstall elaichi@elaichi-skillsUninstall from Settings → PluginsDelete the rule from Settings → Rulesnpx skills remove trutohq/elaichi-skills

Skills

SkillDescription
elaichiWhat Elaichi is, the words it uses, where everything lives in the app, and which skill to load next
elaichi-mcpDrive the MCP endpoint — search_tools, execute_tool and run_code, the connection argument, scopes and refusals, and the missing-tool ladder
elaichi-clientsConnect Claude, ChatGPT, Cursor, Microsoft Copilot or any other MCP client, what to grant on the consent screen, and why a client shows no tools
elaichi-connectionsConnect and look after accounts — sharing versus ownership, status and reconnecting, transfer and offboarding, custom connectors
elaichi-toolboxesCurate what an agent can do — toolboxes versus templates, frozen parameters, what sharing at use delegates, and synthetic tools
elaichi-governanceRoles and the full permission catalog, restrictions, access requests, approvals, the audit log, offboarding, SSO and SCIM
elaichi-automationsWorkflows — triggers and schedules, steps, the draft → dry run → publish loop, runs, approvals and webhooks
elaichi-dataCollections (shared tables), dashboards and public links, and knowledge bases
elaichi-apiWrite code against api.elaichi.ai — auth, the cursor envelope, error shapes, capability fields, CRUD conventions
elaichi-conventionsThe base facts in one page — URLs, auth, pagination, error codes, id prefixes, the two MCP namespaces

Rules (Cursor only)

RuleDescription
elaichiAlways-applied rule with URLs, API auth, the list envelope, error codes, id prefixes and the MCP namespaces

Claude Code plugins have no "always-applied rule" primitive, so the same facts arrive there through the model-invoked elaichi-conventions skill. The rule is generated from that skill by scripts/generate-rule.mjs, and CI fails if the two drift — edit the skill, not the rule.

What is Elaichi?

Elaichi is an agent platform for companies. It connects the software a company already runs on and lets agents do real work in those systems, inside the same permissions the company already grants its people.

Two things carry the product, and most AI tooling offers only one of them: reach — the application catalog, connected once, available as tools an agent can call — and restraint — an agent never getting more access than the person it acts for.

The reach is delivered over MCP. The AI client makes one connection, to Elaichi; the apps are connected inside Elaichi, not inside the client:

Your AI client  ──one connection──►  Elaichi  ──►  Slack
                                              ──►  Jira
                                              ──►  HubSpot

Because every call travels through Elaichi:

  • Access follows the person's role. Toolboxes, teams and per-user overrides all still apply.
  • Restrictions are enforced. A blocked tool is never offered and never runs.
  • Everything is audited, with an AI actor recorded as a field rather than inferred.
  • Revoking is one action, and it takes effect on the client's next call.

What you get

  • A large connector catalog — see elaichi.ai/connectors — plus custom connectors an organization authors or forks
  • Toolboxes and templates — curate tools, rename them for the model, freeze the parameters that are not its decision, and share
  • Synthetic tools — chain several calls into one tool an agent calls once
  • Delegated execution — share a toolbox and colleagues run your accounts without ever seeing a credential
  • 58 permissions, 8 predefined roles plus unlimited custom roles, per-tool restrictions, and an append-only audit log — all of it applying over MCP too
  • SSO, SCIM and directory group mapping
  • Three plans — Personal (free, for one person), Gold and Black, each including the one before; every new workspace starts on a 14-day Black trial. See elaichi.ai/pricing

Resources

Changelog

See CHANGELOG.md.

License

Apache-2.0 — see LICENSE.

Comments

Markdown supported

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.