# Claude MCP servers for data work: how to add and vet them

How to add MCP servers to Claude Code for search, scraping, SEO and enrichment data, what to check before you trust one, and how to keep the tool list short.

## Summary

You use Claude for real work now, and the work needs data it does not have. Search results, a list of companies, a competitor's keywords, a creator's recent posts. The answer in the docs is "add an MCP server". The answer you need is which ones, how many, and how to avoid a setup that grows into a mess.

This post covers Claude MCP servers for data work. It shows the command to add one, the checks to run on any server before you give it access, the reason fewer is better, and a prompt that tests the whole setup in one go.

## What are Claude MCP servers?

An MCP server is a program or a hosted endpoint that gives Claude a set of tools over the Model Context Protocol. Claude lists the tools, decides when to use one, and calls it with the arguments it fills in. If the term is new, [what is an MCP server](https://looot.ai/blog/what-is-an-mcp-server) explains the protocol in plain words.

For data work, the tools usually fall into five groups: web search, page scraping, SEO and keyword data, company and people enrichment, and social data. One server can cover one group or several.

## How do I add an MCP server to Claude Code?

You add a server with a command or a config entry, then restart the session so Claude sees the tools. For a hosted server that speaks streamable HTTP, the command has this shape:

That adds the looot server. The looot CLI can also print a ready-to-paste config for your client with `looot mcp install --client claude-code`. Either way, the first use opens a browser sign-in. A headless agent uses a bearer token created in the dashboard instead.

Check the connection by asking Claude to list the tools it has from the new server. If the list is empty, the connection failed, and the fix is in the server's address or your sign-in, not in the prompt.

## Which MCP servers does a data task need?

Start from the job, not from a directory of servers. Write down the three data jobs you do most, then find the smallest set of servers that covers them.

| If the job is | The tool you need | Where to look |
|---|---|---|
| Find pages on a topic | Web search | Search providers such as Exa and Tavily |
| Turn a page into clean text | Page scraping | Scraping providers such as Firecrawl and Jina |
| Keyword and SERP data | SEO data | SERP API ranking |
| A work email or a company record | Enrichment | Data enrichment use case |
| Posts, comments, profiles | Social data | The platform guides in this blog |

The providers behind those rows are in [the public catalog](https://looot.ai/public-catalog), so one looot connection reaches them. Start with that one server and add a direct one only when you need a feature the catalog lacks.

## How many MCP servers is too many?

More than you can name from memory is too many. Every server adds tool descriptions to Claude's context, and a long list makes the model slower and worse at choosing. The cost shows up as wrong tool picks, not as an error.

A simple rule works well. Keep one general server for data jobs and one or two for tools you own. If you find yourself adding a fourth data server, ask whether a gateway would replace three of them. [The MCP gateway post](https://looot.ai/blog/mcp-gateway-for-agents) explains when that makes sense.

## What should I check before I trust an MCP server?

A server runs with the access you give it, so vet it like a dependency. Ask five questions, and write the answers down.

1. **Who runs it?** A hosted server means a company handles your calls and sees your inputs. A local server runs on your machine and sees what you let it read.
2. **What can it do?** List its tools. A read-only search tool is low risk. A tool that sends email or writes files is not.
3. **What does it need?** Note the tokens and scopes. Give the narrowest scope that works.
4. **What does a call cost?** Find out before the agent loops. A tool that bills per call needs a spend limit.
5. **Can you see what ran?** You want a log of calls, with inputs and costs, that you can read afterward.

For looot, the answers are as follows. A hosted gateway runs the calls. The agent can search and inspect for free and run endpoints that bill per call. The token has scopes for reading the catalog, reading runs and executing runs. Every endpoint shows its price before it runs, and `looot runs get` returns the cost of a finished call.

## What does a data job look like end to end?

Take a small job: "find ten companies that sell project software to agencies and get a contact for each." Claude does not hold that data, so it uses the tools you connected.

First it calls a search tool for pages about agency project software and reads the results. Then it asks the catalog for a company search endpoint and a work email endpoint, and reads each price. It runs the search, picks ten companies, and calls the email endpoint for each name. At the end it writes a table with the company, the contact, the source endpoint and the cost.

Three habits make this reliable. Put the budget in the prompt. Ask for the source and cost on every row. And read the first three rows by hand before you accept the other seven. A model fills gaps with confident guesses, and the cheapest check is a person reading a few rows.

[The Clay replacement post](https://looot.ai/blog/can-an-ai-agent-replace-clay) walks through a longer version of this job, with the places where an agent falls short.

## Try it: a prompt that tests the setup

Run this after you add the server. It uses only free calls, so it tests the connection without spending anything.

If the answer to step 4 names a gap, add the next server for that gap and rerun the prompt.

## What it cannot do

- A server does not make Claude correct. The model can still misread a result, so check any number you plan to publish.
- It does not give Claude access to your private data unless you connect it. A hosted data server sees only what the agent sends.
- It does not run work while Claude is idle. Anything that needs a timer needs scheduled runs, not available yet.
- It does not cap spend unless you set a cap. Tell the agent a limit in the prompt, and set a budget on the token where the server supports one.

Last checked 2026-10-03 against the looot skill file and the live catalog. Author: the looot team.

## Questions

### What are the best MCP servers for Claude Code?

It depends on the job. For data work, pick one general server that covers search, scraping, SEO and enrichment, then add a specialist only for a gap. Fewer servers keep the tool list short and the model accurate.

### How do I add an MCP server to Claude?

In Claude Code, run `claude mcp add` with the server's name and address, then restart the session. For looot, the address is https://api.looot.ai/mcp, and the first use opens a browser sign-in.

### How many MCP servers can Claude handle?

There is no fixed limit, but quality drops as the tool list grows. A good working number is one general data server plus one or two you own. Past that, consider a gateway.

### Are MCP servers safe to use with Claude?

They are as safe as the access you grant. Check who runs the server, which tools it exposes, which scopes it needs and whether you can read a log of its calls. Give the narrowest scope that works.

### Do Claude MCP servers cost money?

Some do and some do not. A server that calls paid data providers bills per call. With looot, searching and inspecting are free, and a run shows its price first. There is no trial credit, so top up before the first run.

### Does Cursor work the same way?

The protocol is the same, so a hosted server like looot works in Cursor too. The way you add it differs by client. Check your client's MCP settings, or the looot setup page, for the exact steps.

## For agents

### Code (bash)

```bash
claude mcp add --transport http looot https://api.looot.ai/mcp
```

### Test my data setup

```text
Use looot to check my data setup in Claude Code.
1. Set up https://looot.ai/skill.md.
2. List every MCP server you have and the tools each one gives you.
3. For the looot server, search the catalog for "web search" and "google keyword search volume". Inspect one endpoint for each and show me the input fields and the price. Do not run anything.
4. Tell me which of my data jobs this setup covers and which it does not.
```