Xevol

com.xevolPublished by xevol.comOfficial publisherv0.16.1Updated Nov 1, 2026

Search and read your Xevol contacts, companies and deals from your AI agent.

VerifiedStreamable HTTPWeb executableProductivity & Workflow Business & Commerce

Server details

Identifier: com.xevol/xevol
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Nov 1, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to xevol.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.xevol%2Fxevol.svg)](https://sourceweft.com/mcp/com.xevol%2Fxevol?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Xevol connects an AI assistant to one Xevol Workspace to search and read contacts, companies and deals, and to draft work a person then approves.

What you can do: Search and read contacts, companies and deals in a single Xevol Workspace
Draft work in that Workspace for a person to review
Act with the approving user's rights in that Workspace, with sending, publishing and deleting left to a person
Use a read-only address that only searches and reads and changes nothing
When to use it: Useful when your CRM-style contacts, companies and deals live in Xevol and you want an assistant to look them up or prepare drafts inside one Workspace, especially through a read-only connection for directory listings.
Requirements: A Xevol account and a paid Workspace, since agent work uses that Workspace's credits. OAuth 2.1 sign-in with PKCE and dynamic client registration over streamable HTTP; approve a sign-in code in a browser and pick one Workspace. Connections last six months before re-signing in.

Before you install

The agent acts with your rights in the chosen Workspace, and anything it starts spends that Workspace's credits. Sending, publishing and deleting are reserved for a person, but drafts and reads still expose contact, company and deal data to the assistant. Review connected agents in Settings and remove ones you no longer use; removing one stops its token.

Installation

In SourceWeft

Open Xevol 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.xevol%2Fxevol/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.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "xevol": {
      "type": "http",
      "url": "https://xevol.com/api/mcp/listed"
    }
  }
}

README

Xevol MCP server

Connect Claude, ChatGPT, Codex, Claude Code or pi to one Xevol Workspace. Your agent reads and drafts there. A person approves, sends, publishes and deletes.

This repository holds documentation only. The server runs at xevol.com; its source is private.

Connect

Coding agents (claude, codex or pi):

The command shows a sign-in code. Approve it in any browser and pick a Workspace. npx xevol connect other prints the URL and header for any other MCP client.

Apps that accept an MCP server URL, such as ChatGPT or Claude:

Directory listings use a read-only address. It searches and reads contacts, companies and deals in one Workspace, and changes nothing. A sign-in here gives a token that works on this address only:

How it works

Sign-in: OAuth 2.1 with PKCE and dynamic client registration, over streamable HTTP.
Scope: one Workspace per connection, fixed when you approve. The agent acts with your rights there.
Paid work: anything the agent starts uses that Workspace's credits.
Lifetime: a connection lasts six months, then you sign in again.
Control: Settings lists each connected agent. Remove one and its token stops working.

You need a Xevol account. See pricing.

Links

Source: README.md at commit 54de840

Tools

This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

v0.16.1LatestNov 1, 2026
v0.16.0Nov 1, 2026

Score

75% 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
Declare a license in the repository or the registry entry.