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
- 01One endpoint for connected company apps
- 02Role-based access and restrictions
- 03Auditable tool calls
- 04Toolboxes and synthetic tools
- 05SSO, SCIM, and directory groups
Use cases
- 01Let agents act in connected business apps
- 02Limit available tools by role
- 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.
https://api.elaichi.ai/mcpclaude mcp add --transport http elaichi-5f074d https://api.elaichi.ai/mcp{"mcpServers":{"elaichi-5f074d":{"type":"http","url":"https://api.elaichi.ai/mcp"}}}Open in Cursor{"servers":{"elaichi-5f074d":{"type":"http","url":"https://api.elaichi.ai/mcp"}}}Open in VS Code{"mcpServers":{"elaichi-5f074d":{"type":"http","url":"https://api.elaichi.ai/mcp"}}}{"mcpServers":{"elaichi-5f074d":{"serverUrl":"https://api.elaichi.ai/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 README
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 Code | Cursor (marketplace) | Cursor (remote rule) | npx skills | |
|---|---|---|---|---|
| Update | /plugin marketplace update elaichi-skills | Managed by the marketplace | Re-sync the remote rule from Settings → Rules | npx skills update |
| Remove | /plugin uninstall elaichi@elaichi-skills | Uninstall from Settings → Plugins | Delete the rule from Settings → Rules | npx skills remove trutohq/elaichi-skills |
Skills
| Skill | Description |
|---|---|
| elaichi | What Elaichi is, the words it uses, where everything lives in the app, and which skill to load next |
| elaichi-mcp | Drive the MCP endpoint — search_tools, execute_tool and run_code, the connection argument, scopes and refusals, and the missing-tool ladder |
| elaichi-clients | Connect 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-connections | Connect and look after accounts — sharing versus ownership, status and reconnecting, transfer and offboarding, custom connectors |
| elaichi-toolboxes | Curate what an agent can do — toolboxes versus templates, frozen parameters, what sharing at use delegates, and synthetic tools |
| elaichi-governance | Roles and the full permission catalog, restrictions, access requests, approvals, the audit log, offboarding, SSO and SCIM |
| elaichi-automations | Workflows — triggers and schedules, steps, the draft → dry run → publish loop, runs, approvals and webhooks |
| elaichi-data | Collections (shared tables), dashboards and public links, and knowledge bases |
| elaichi-api | Write code against api.elaichi.ai — auth, the cursor envelope, error shapes, capability fields, CRUD conventions |
| elaichi-conventions | The base facts in one page — URLs, auth, pagination, error codes, id prefixes, the two MCP namespaces |
Rules (Cursor only)
| Rule | Description |
|---|---|
| elaichi | Always-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
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.