
QuiQSol
com.quiqsolPublished by quiqsol.comOfficial publisherv1.0.0Updated Oct 29, 2026
Work in QuiQSol from any AI agent: CRM, Help Desk, inbox, invoices, projects, forms and analytics.
Overview
Connects an AI assistant to a QuiQSol workspace so it can read and act on CRM, help desk, inbox, invoices, projects, forms and analytics.
- What you can do
- Search, read and update CRM records: leads, contacts, companies, deals, notes, tasks and pipeline stages
- List and read help desk tickets with conversations, reply with a preview, add internal notes, change status
- List inbox conversations across WhatsApp, website chat and social, and reply within the WhatsApp 24-hour window
- List and read invoices and totals, create draft invoices and send them after a preview
- List projects and tasks and create or update tasks; list forms and submissions
- Read business overview, sales, help desk and invoice analytics summaries
- When to use it
- Useful when a team works inside QuiQSol and wants an assistant to look up customer records, draft replies or invoices, or pull business summaries without switching apps. Scoped keys let you limit an agent to read-only or specific products.
- Requirements
- Either the remote endpoint with OAuth sign-in, or the npm package @quiqsol/mcp run with Node.js 18 or later over stdio. Local and header-based setups need a QuiQSol AI agent API key in QUIQSOL_API_KEY, created in Settings > Developer Platform with chosen scopes. Network access to the QuiQSol API.
Installation
In SourceWeft
- Open QuiQSol in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.quiqsol%2Fquiqsol/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"quiqsol": {
"type": "http",
"url": "https://api.quiqsol.com/mcp"
}
}
}README
@quiqsol/mcp
Connect QuiQSol to Claude, ChatGPT, Cursor and any AI agent.
This package gives you two things:
quiqsol mcp: a local Model Context Protocol server over stdio, for apps that launch a command (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code).quiqsol: a command line for your terminal, scripts and agents, with JSON output.
Both run on the QuiQSol remote MCP server at https://api.quiqsol.com/mcp. Tools, permissions and safety rules live on the server, so this package stays small, has zero dependencies and never needs an update to gain new tools.
MIT licensed.
What your agent can do
Security model
- Scoped access. Every key and connection carries explicit scopes (
crm:read,crm:write,helpdesk:read,helpdesk:write,inbox:read,inbox:send,invoices:read,invoices:write,invoices:send,projects:read,projects:write,forms:read,analytics:read). An agent only sees the tools its scopes allow. - Your own permissions. An agent acts as the person who created the key or approved the connection, inside that person's role. It can never do more than they can in the app.
- Nothing reaches a customer without approval. Ticket replies, inbox replies and invoice sends return a preview first. They only go out when called again with
confirm: true, which agents are instructed to do only after you approve. - Untrusted content is labelled. Every result is wrapped as workspace data, with customer-written text marked as data, never instructions.
- No secrets in output. Tokens, hashes and keys are stripped from every result server-side.
- Revocable and audited. Revoke any key or connection in Settings > Developer Platform. Every call is listed in the API activity log there.
Get a key
In QuiQSol, open Settings > Developer Platform > AI agents, choose Create AI agent key, pick the scopes and copy the key (shown once).
Claude and ChatGPT do not need a key: add https://api.quiqsol.com/mcp as a connector and sign in with OAuth. See the setup guide.
Use with Claude Desktop, Cursor or any stdio MCP client
Claude Desktop: Settings > Developer > Edit Config. Cursor: ~/.cursor/mcp.json or Settings > MCP.
Clients that support remote servers can skip the package and point straight at the server:
Claude Code:
Use the CLI
Any tool, by name:
Output is JSON on stdout (pretty in a terminal, compact when piped). Commands that reach a customer show a preview and ask before sending; in scripts they print the preview and exit with code 3 unless you pass --yes.
Configuration: QUIQSOL_API_KEY and QUIQSOL_API_URL override the saved login in ~/.config/quiqsol/config.json (written with owner-only permissions).
Use from code
Prefer plain HTTP? The same tools are available as REST at https://api.quiqsol.com/public/v1/agent (GET /tools, POST /tools/{name}).
Requirements
Node.js 18 or later.
License
MIT. The QuiQSol platform itself is a commercial service; this connector is open source so you can read exactly what runs on your machine.
Source: README.md at commit e3d23e1
Tools
0Version history
1- v1.0.0LatestOct 29, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts