Kenda MCP Server

by kenda-co Your server? Claim it

local only

Kenda runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from pypi.

Read-only MCP server for querying Kenda token spend and waste

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 27 · avg 13 · +18% w/w

a month agotoday

103

Installs / week

pypi · ingestion-mcp

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add ingestion-mcp -- uvx ingestion-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ingestion-mcp": {
      "command": "uvx",
      "args": [
        "ingestion-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.ingestion-mcp]
command = "uvx"
args = ["ingestion-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "ingestion-mcp": {
      "command": "uvx",
      "args": [
        "ingestion-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "ingestion-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ingestion-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: KENDA_ENDPOINT (Kenda API base URL, e.g. https://api.kenda.app. Optional: normally read from ~/.kenda/config.json, which `kenda-collect init` writes. Set this to override the file), KENDA_TOKEN (Per-customer Kenda ingest token (kenda_...). Optional: normally read from ~/.kenda/config.json. Set this to override the file).

Alternatives to Kenda

same job, measured the same way

Stripe MCP

by robinafaruqia

Read-only MCP server for querying Stripe customers, payments, and invoices.

41 installs/wk local only

SEO Tools: Yandex.Webmaster

by antohins

MCP server for Yandex.Webmaster search queries (read-only).

113 installs/wk local only

OddsRelay

by oddsrelay

Read-only MCP server for OddsRelay odds data, with a token cap on every call that spends tokens.

221 installs/wk local only

Osm Tagging Schema MCP

by gander-tools

MCP server for querying and validating OpenStreetMap tags

82 installs/wk local only

Elekto MCP for SQL Server

by elekto-com-br

Read-only SQL Server introspection and querying: schema, definitions, dependencies and data.

local only

MCP Registry MCP Server

by wei

MCP server for querying the official MCP registry.

40 installs/wk local only

1C OData MCP

by alexgrebeshok-coder

Read-only MCP server for 1C:Enterprise via OData with metadata and query builder tools.

46 installs/wk local only

RZ AI Labs

by rzailabs

Read-only MCP server for RZ AI Labs — query its services, workshops, and contact info.

4 tools answering

Kenda — questions

Answers built from our own checks of this server.

Why is there no uptime for Kenda?

Kenda runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package ingestion-mcp was installed 103 times last week.

Is Kenda still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect Kenda?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls ingestion-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Kenda?

The pypi package ingestion-mcp was installed 103 times in the last week. Week over week that is +18%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.