Click on "Install 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., "@apollo-io-mcp-server Find senior engineers at Google"
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.
This project provides an MCP server that exposes the Apollo.io API functionalities as tools. It allows you to interact with the Apollo.io API using the Model Context Protocol (MCP).
The project consists of the following main components:
apollo_client.py: Defines the ApolloClient class, which is used to interact with the Apollo.io API. It includes methods for people enrichment, organization enrichment, people search, organization search, and organization job postings.
server.py: Defines the FastMCP server, which exposes the Apollo.io API functionalities as tools. It uses the ApolloClient class defined in apollo_client.py to interact with the API.
apollo/: Contains the data models for the Apollo.io API, such as PeopleEnrichmentQuery, OrganizationEnrichmentQuery, PeopleSearchQuery, OrganizationSearchQuery, and OrganizationJobPostingsQuery.
Related MCP server: Apollo.io MCP Server
The following functionalities are exposed as MCP tools:
people_enrichment: Use the People Enrichment endpoint to enrich data for 1 person.
organization_enrichment: Use the Organization Enrichment endpoint to enrich data for 1 company.
people_search: Use the People Search endpoint to find people.
organization_search: Use the Organization Search endpoint to find organizations.
organization_job_postings: Use the Organization Job Postings endpoint to find job postings for a specific organization.
To use this MCP server, you need to:
Set the APOLLO_IO_API_KEY environment variable with your Apollo.io API key. Or create '.env' file in the project root with APOLLO_IO_API_KEY.
Get dependencies: uv sync
Run the uv run mcp run server.py
The apollo/ directory contains the data models for the Apollo.io API. These models are used to define the input and output of the MCP tools.
apollo/people.py: Defines the data models for the People Enrichment endpoint.
apollo/organization.py: Defines the data models for the Organization Enrichment endpoint.
apollo/people_search.py: Defines the data models for the People Search endpoint.
apollo/organization_search.py: Defines the data models for the Organization Search endpoint.
apollo/organization_job_postings.py: Defines the data models for the Organization Job Postings endpoint.
To test, set APOLLO_IO_API_KEY environment variable and run uv run apollo_client.py.
Configure Claude for Desktop to use these MCP servers by adding them to your claude_desktop_config.json file:
{
"mcpServers": {
"apollo-io-mcp-server": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"mcp",
"run",
"path/to/apollo-io-mcp-server/server.py"
]
}
}
}Use the Organization Enrichment endpoint to enrich data for 1 company.
https://docs.apollo.io/reference/organization-enrichment
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description should disclose behavioral traits like read-only status, prerequisites, or return structure. It merely states 'enrich data' without mentioning if it modifies data or what the response contains.
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 very short (one sentence plus link), which is concise but sacrifices completeness. The link to docs is helpful but not part of the inline description. It front-loads the purpose but lacks depth.
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 single parameter and no output schema, the description is incomplete. It does not explain what enrichment results look like or how to handle the response. Sibling tools exist, but no comparative context is provided.
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 description adds no meaning beyond the input schema. The 'query' parameter is not explained, though its nested 'domain' field has a schema description. With 0% schema description coverage on the main parameter, the description should compensate but fails.
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 tool enriches data for one company, using a specific verb (enrich) and resource (company). It distinguishes from siblings like organization_search (searching) and organization_job_postings (job listings). However, it could be more specific about what 'enrich' entails (e.g., company details, funding).
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 provided on when to use this tool vs. alternatives like organization_search or people_enrichment. The description only states what it does without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use the Organization Job Postings endpoint to find job postings for a specific organization.
https://docs.apollo.io/reference/organization-jobs-postings
| Name | Required | Description | Default |
|---|---|---|---|
| organization_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior fully. It only says 'find job postings' with no mention of limitations, pagination, error conditions, or what happens if the organization_id is invalid.
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 very concise with one sentence and a link, front-loading the purpose. However, it is too brief and omits necessary details, reducing informativeness.
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 no output schema and a simple parameter, the description fails to mention return format, expected results, or any constraints. It is incomplete for an agent to invoke correctly.
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 schema has 0% description coverage for the sole parameter organization_id. The description does not add any meaning beyond the parameter name; it doesn't explain what the ID represents or how to obtain it.
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 'find' and resource 'job postings', scoped to a specific organization, distinguishing it from sibling tools like organization_enrichment or people_search.
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 versus alternatives like organization_enrichment or organization_search. The description simply states what it does without context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use the Organization Search endpoint to find organizations.
https://docs.apollo.io/reference/organization-search
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description fails to disclose any behavioral traits such as pagination behavior, rate limits, data freshness, or whether results are sorted. The link to external docs does not compensate for the lack of explicit information.
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 short (two sentences) and includes a helpful URL, but it lacks structure. The purpose is clear, but it does not front-load key information or use formatting to improve readability.
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 complexity of the input schema (many nested parameters) and no output schema, the description is insufficient. It does not explain what the search returns, how to interpret results, or any limitations. The link partially compensates but the description itself is incomplete.
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 tool description adds no value beyond the schema. Although the nested fields in the schema have detailed descriptions, the top-level 'query' parameter is undocumented in the description, and the description does not explain how to construct the query object.
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?
Description clearly states it is for finding organizations using an API endpoint. The sibling tool names (organization_enrichment, organization_job_postings, people_enrichment, people_search) help distinguish its purpose as a search tool.
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 provided on when to use this tool versus alternatives like organization_enrichment or people_search. The description does not mention any prerequisites, filters, or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use the People Enrichment endpoint to enrich data for 1 person.
https://docs.apollo.io/reference/people-enrichment
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description provides no behavioral information. It does not disclose whether the tool consumes credits, requires authentication, has rate limits, or produces side effects. The agent gains no insight beyond the basic action.
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 extremely concise: one sentence and a link. It front-loads the action efficiently and wastes no words. However, it is so brief that it omits critical context.
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 lack of annotations, output schema, and any parameter guidance in the description, the tool is severely under-described. The single sentence 'enrich data for 1 person' is insufficient for an agent to understand how to use it effectively, leaving major gaps in contextual understanding.
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 description adds no parameter information; it does not mention any of the input fields. Although the schema itself has detailed parameter descriptions, the description fails to add value beyond that. With 0% schema description coverage, this is a significant gap.
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 states the tool enriches data for a single person, which clearly distinguishes it from sibling tools like people_search (searching multiple) and organization_enrichment. However, it does not specify what kind of data is enriched (e.g., contact info, employment), making it slightly vague.
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 usage guidance is provided. The description does not indicate when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. The agent is left without context for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use the People Search endpoint to find people.
https://docs.apollo.io/reference/people-search
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. However, it only states 'find people' without mentioning read-only nature, rate limits, authentication needs, or any side effects. The external link does not compensate for the lack of inline transparency.
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 extremely short—one sentence and a URL. While concise, it under-specifies the tool's functionality for a complex parameter set. The sentence is front-loaded, but it does not earn its place as it lacks detail; an external link is not a substitute for inline explanation.
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 complexity (many parameters, no annotations, no output schema), the description is severely incomplete. It does not explain return values, pagination, or any behavioral context. The external documentation link is not part of the description text.
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 description adds no parameter information beyond what is already in the input schema. The top-level 'query' parameter has no description, and the sub-properties are well documented in the schema, but the description does not explain how to construct the query object or provide examples. With 0% schema description coverage, the description fails to compensate.
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 'find' and resource 'people', making the basic purpose obvious. It distinguishes from sibling tools like organization_search (which searches organizations) and people_enrichment (which enriches specific people).
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 is provided on when to use this tool versus alternatives such as people_enrichment or organization_search. There is no mention of prerequisites or context, leaving the agent to infer usage solely from the tool name and siblings.
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. Dates show when Glama detected each change.
v0.1.0organization_enrichmentorganization_job_postingsorganization_searchpeople_enrichmentpeople_searchEach tool targets a distinct entity and operation: organization enrichment, job postings, search; people enrichment and search. No overlapping purposes.
All tools use a consistent pattern of <entity>_<operation> in snake_case, with operations like enrichment, search, and job_postings.
With 5 tools covering the two main domains (organizations and people) and key operations (search and enrichment), the count is well-scoped.
The tool set provides search and enrichment for both entities, plus job postings for organizations. No obvious gaps for the intended sales intelligence use case.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Prospect, enrich leads, and manage outreach sequences with Apollo.io.
Official ZoomInfo MCP server. Search and enrich companies, contacts, and buyer intent signals.
LinkedIn outreach MCP server — 19 tools for AI agents to prospect, sequence, and manage contacts.
LeadOracle - 7-tool B2B lead intel MCP: enrichment, scoring, intent signals, ICP fit.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/edwardchoh/apollo-io-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
