This server provides free company data for AI agents via MCP tools, enabling company research, technology tracking, and contact discovery.
Search companies by name, sector, size, B2B/B2C, technology, country, or keyword to build prospect lists.
Look up a company's full record by domain: tech stack, verified emails (SMTP-scored), people, web signals, and company details (1 reveal per domain per 30 days with API key).
Find people by title, seniority, department, company filters, and email confidence; returns SMTP-verified emails.
Get a specific person by ID, including email (free if company was revealed recently).
Browse technologies — top 100 by company count, or list companies using a specific technology.
Get switch signals — companies that added/removed/switched tools (tech_switch) or people changing jobs (career_move), indicating buying intent.
Check usage — plan, reveals, requests, and companies left today (free, no key needed).
Works with anonymous access for company/tech/signal tools; emails and people require a free API key.
Supports stdio and Streamable HTTP transports, with rate limits and daily quotas.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AgentData MCP Server Look up acme.com for their tech stack and key people"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Free company data for AI agents, as MCP tools. AgentData profiles companies from the public web: tech stacks, web signals (pricing page, free trial, API docs, careers), email addresses with their verification status, people with titles, and switch signals (who just dropped or adopted a tool).
Works with Claude, Claude Code, ChatGPT, Codex, Gemini, Cursor, Windsurf, VS Code, GitHub Copilot, Zed, Cline and any other MCP client.
No key is needed to search companies, browse technologies or read switch signals. Emails and people need a free API key (1,000 contact reveals a day, no card): sign up at agentdata.run/signup and copy the key from agentdata.run/settings.
claude mcp add agentdata -- npx -y agentdata-mcp-server --api-key YOUR_API_KEYAdd to the client's MCP config (claude_desktop_config.json, .cursor/mcp.json, mcp.json):
{
"mcpServers": {
"agentdata": {
"command": "npx",
"args": ["-y", "agentdata-mcp-server", "--api-key", "YOUR_API_KEY"]
}
}
}Leave out --api-key to run anonymously (company, technology and signal tools only).
https://mcp.agentdata.run/mcpStreamable HTTP. Send Authorization: Bearer YOUR_API_KEY for emails and people; without a header it serves the anonymous tools. In Claude Code:
claude mcp add agentdata --transport http https://mcp.agentdata.run/mcp --header "Authorization: Bearer YOUR_API_KEY"Related MCP server: Outscraper MCP
Tool | What it returns | Cost | Key |
| Companies by name or by sector, size, b2b/b2c, model, technology, country | none | no |
| The technology index, or companies using one technology | none | no |
| Companies that added, removed or switched a tool; growth and hiring changes | none | no |
| One domain's full record: company, tech stack, signals, email pattern, email addresses, people | 1 reveal per domain per 30 days | yes |
| People by title, seniority, department, company filters | 1 reveal per company in the response | yes |
| One person by id, with email | 1 reveal (free if the company was revealed in the last 30 days) | yes |
| Plan and what is left today | none | no |
Every response ends with a usage line (reveals, requests and companies left), so an agent can pace itself. A domain that has not been profiled yet is queued at the front of the crawl and answers "retry in about two minutes" without charging.
Anonymous | Free key | Pro ($99 a year) | |
Contact reveals a day | none | 1,000 | 10,000 |
Requests per 5 hours | 300 | 5,000 | 25,000 |
Requests a second | 2 | 5 | 20 |
Distinct companies a day | 200 | 5,000 | 25,000 |
Nothing else is metered. Details at agentdata.run/pricing.
"Which SaaS companies use Intercom? Give me small ones with a pricing page."
"Look up linear.app: tech stack, and who runs engineering."
"Who dropped Zendesk in the last 30 days?"
"Find heads of sales at fintech companies that use HubSpot, with email addresses."
"How many contact reveals do I have left today?"
npm install
npm run build
node dist/index.js --api-key YOUR_API_KEY # stdio
node dist/index.js --http --port 3001 # Streamable HTTP on POST /mcp, 127.0.0.1 only
node dist/index.js --helpAGENTDATA_API_KEY, PORT and HOST work as environment variables. npm run inspect opens the MCP Inspector.
The HTTP server binds to 127.0.0.1 by default and only answers local pages, so a key you start it with cannot be used by other sites or other machines. --host 0.0.0.0 makes it public; in that mode the startup key is ignored and every caller must send its own Authorization: Bearer key.
Website: agentdata.run
How it works: agentdata.run/how-it-works
API docs: agentdata.run/docs
The data, as it is: agentdata.run/data
How it compares: the best MCP servers for sales, 12 compared
MIT licence.
Check your current plan, lookup balance, and remaining quota. Free — does not consume a lookup.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes it as free and non-consumptive, which are key behavioral traits. No annotations, so description carries burden; it suffices for a read-only check.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a zero-parameter, read-only tool. Describes inputs (none) and outputs (plan, balance, quota) sufficiently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; baseline score of 4 applies as per rules.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it checks plan, balance, and quota. Distinct from sibling tools which focus on people, signals, or companies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Indicates it is free and does not consume a lookup, implying safe usage. No explicit when-not-to-use, but given simplicity, it's clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for people at companies. Filter by title, seniority, department, or company attributes like sector and technology. Emails are SMTP-verified with confidence scores.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | Company domain to search within | |
| title | No | Job title filter | |
| seniority | No | Seniority level: c-level, vp, director, manager, individual | |
| department | No | Department filter | |
| has_email | No | Only return people with verified emails | |
| sector | No | Company sector filter | |
| tech | No | Technology the company uses | |
| limit | No | Max results to return | |
| email_confidence | No | Email confidence filter: high (80+), medium (50-79), low (below 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must disclose behavioral traits. It mentions that emails are SMTP-verified with confidence scores, but fails to explain return format, pagination, or any constraints. The tool is apparently read-only, but this is not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at two sentences, front-loaded with the main action. No unnecessary words, but could be marginally more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 9 parameters, no required fields, and no output schema, the description covers filters and email verification but lacks guidance on usage boundaries, result handling, or ordering. It is somewhat incomplete for a complex search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description restates some filter parameters but adds the email confidence score mention. It does not provide additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search for people at companies') and specifies the resource. It details filters (title, seniority, department, company attributes) and mentions email verification, differentiating it from sibling tools like 'search_companies' which search for companies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks explicit guidance on when to use this tool versus alternatives. It does not mention when not to use it or provide context for selection among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get technology switch signals (companies changing tools) and career moves (people changing jobs). Shows buying intent and market movement.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Signal type: tech_switch or career_move | |
| moved_from | No | Technology or company moved from | |
| moved_to | No | Technology or company moved to | |
| sector | No | Filter by sector | |
| days | No | Lookback period in days | |
| limit | No | Max results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not mention pagination, rate limits, data recency, or what happens with missing parameters. The phrase 'shows buying intent' is vague.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the key purpose. No wasted words; every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema or annotations, and the description omits details like return format, error handling, or behavior when filters are combined. For a tool with 6 optional parameters, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter described in the schema. The description adds no additional meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves technology switch signals and career moves, and mentions 'buying intent and market movement,' which distinguishes it from sibling tools like check_usage or find_people. However, it could be more precise about the scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives (e.g., find_people for people data) or what prerequisites exist. The description implies market analysis but lacks explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Browse detected technologies. Without a slug, returns the top 100 technologies by company count. With a slug, returns companies using that specific technology.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | Technology slug (e.g. react, stripe, intercom) | |
| page | No | Page number for pagination |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses basic behavior (returns top 100 without slug, companies with slug) but omits details like pagination behavior, rate limits, authentication requirements, or what happens with invalid slugs. The 'page' parameter exists but its usage and default page size are not explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two concise, well-structured sentences. The first sentence immediately states the tool's purpose. No extraneous information is included.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema), the description covers the main functional behavior. It explains both input modes and their corresponding outputs. However, it lacks details on pagination limits, company count per page, and the structure of returned data, which would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters with descriptions. The description adds value by providing examples for 'slug' (e.g., react, stripe) and mentioning pagination for 'page', but does not clarify pagination specifics such as items per page or page number limits. Since schema coverage is 100%, the description provides marginal added meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'browse' and resource 'technologies'. It distinguishes two modes based on the presence of a slug, providing specific behavior for each mode. However, it does not explicitly differentiate from sibling tools like 'check_usage' or 'lookup_company', which could also involve technologies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (without slug for top technologies, with slug for specific technology usage) but offers no explicit guidance on when not to use it or comparisons to sibling tools. There is no mention of alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full company enrichment for a domain — tech stack, verified emails, team members, web signals, and company details. Emails are verified via SMTP and scored 0-95. Free provider emails (gmail, yahoo) are excluded.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Company domain to look up (e.g. stripe.com) | |
| min_confidence | No | Minimum email confidence score 0-95. Default 50 filters out invalid and low-quality emails. Use 90 for outreach-safe emails only. | |
| verification_status | No | Filter emails by verification status. Comma-separated. Values: valid, catch-all, catch-all-unknown, unknown. Example: 'valid,catch-all' for confirmed deliverable emails. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: emails are SMTP-verified, scored 0-95, free providers excluded. It implies a read operation and gives details on output content. It does not mention rate limits or auth but is sufficient for a typical enrichment tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no redundancy. The first sentence immediately states the primary purpose and output components. Second sentence adds critical detail on email verification. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but the description lists the major output categories (tech stack, emails, team, signals, details). This provides sufficient context for an agent to understand what is returned. Could mention limits but not essential for this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by clarifying default for min_confidence (50), suggesting 90 for outreach-safe, and explaining verification_status format. These details aid correct parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'get', the resource 'full company enrichment', and scope 'for a domain'. It lists specific enrichments (tech stack, verified emails, team members, web signals, company details), distinguishing it from sibling tools that focus on individual aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use via its comprehensive nature, but does not explicitly state when not to use or mention siblings. It provides context on email verification and exclusion of free providers, which helps in deciding suitability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find companies matching filters. Use for building prospect lists by sector, size, technology, or keyword search.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Keyword search query | |
| sector | No | Industry sector filter | |
| vertical | No | Business vertical filter | |
| size | No | Company size: micro, small, medium, large | |
| b2b_b2c | No | Business model: B2B, B2C, or both | |
| tech | No | Technology slug to filter by | |
| country | No | Country filter | |
| page | No | Page number for pagination |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral context. It fails to mention pagination behavior, how filters are combined (AND/OR), authentication requirements, or what happens when no results are found. The 'page' parameter hints at pagination but is not explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no redundant words. The first sentence states the core function, the second provides a use case. Ideal length and front-loading for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 8 parameters and no output schema, yet the description is only two sentences. It lacks essential details such as response format, pagination limits, filtering logic, or error handling. For a search tool of this complexity, the description is insufficiently informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description lists the filter types (sector, size, technology, keyword) but adds no semantics beyond the schema's own parameter descriptions. It does not clarify how parameters interact or expected input formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it finds companies matching filters, with specific filter types listed. However, it does not explicitly differentiate its batch search role from the single-company lookup tool (lookup_company), leaving slight ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises using it 'for building prospect lists by sector, size, technology, or keyword search,' giving a concrete use case. But it offers no guidance on when not to use it (e.g., for a single company lookup) and no mention of alternatives among the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.2check_usagefind_peopleget_signalsget_technologieslookup_companysearch_companiesScored across 6 tools
Each tool targets a specific function: account usage, people search, signals, technologies, company details, and company search. While lookup_company includes team members, its primary focus is company enrichment, distinct from find_people's cross-company search. Overlaps are minimal and descriptions clarify boundaries.
All tools follow a consistent verb_noun pattern in snake_case (e.g., find_people, get_signals, search_companies). The naming is predictable and intuitive, with clear action and target.
With 6 tools, the server is well-scoped for its purpose of people and company intelligence. Each tool addresses a distinct need without redundancy, and the count is neither too sparse nor overwhelming.
The tool set covers core workflows: account management, person search, company search and enrichment, technology browsing, and signal tracking. There are no obvious gaps for the intended domain of B2B data enrichment.
Company enrichment for AI agents: firmographics, tech stack, headcount, funding, domain emails.
Search companies, enrich contacts, and reveal emails and phones from your AI agent.
Global B2B intelligence for AI agents: 35M+ companies, 1.6M sanctions, KYB pack. 78 tools.
Paid business, people, company, lead, and web intelligence for autonomous AI agents.
