# How to integrate Sixtyfour MCP with Atomic Agent

```json
{
  "title": "How to integrate Sixtyfour MCP with Atomic Agent",
  "toolkit": "Sixtyfour",
  "toolkit_slug": "sixtyfour",
  "framework": "Atomic Agent",
  "framework_slug": "atomic-agent",
  "url": "https://composio.dev/toolkits/sixtyfour/framework/atomic-agent",
  "markdown_url": "https://composio.dev/toolkits/sixtyfour/framework/atomic-agent.md",
  "updated_at": "2026-11-18T05:40:34.545Z"
}
```

## Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,700+ apps through Composio, including Sixtyfour.
This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Sixtyfour account. See the [Atomic Agent documentation](https://atomicagent.io/docs/?cta_placement=atomic-agent-docs) for installation instructions.
For exact tool slugs and parameter tables, see the [tool catalog in the Composio docs](https://docs.composio.dev/toolkits/sixtyfour).

## Also integrate Sixtyfour with

- [ChatGPT](https://composio.dev/toolkits/sixtyfour/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/sixtyfour/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/sixtyfour/framework/hermes-agent)

## TL;DR

### How Atomic Agent connects to Sixtyfour
Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.
Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

## Connect Sixtyfour to Atomic Agent

### Connect Sixtyfour to Atomic Agent
- Sign up or sign in to the [Composio dashboard](https://dashboard.composio.dev/?cta_placement=atomic-agent-api-key). Copy your API key.
- In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
- Ask Atomic Agent to do something in Sixtyfour. It searches Composio for the right tool.
- On first use, open the sign-in link returned in the chat. Connect your Sixtyfour account, then return to Atomic Agent to continue.
### Headless setup
Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

```bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY
```

## What is the Sixtyfour MCP server, and what's possible with it?

The Sixtyfour MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Sixtyfour account. It provides structured and secure access to people and company search, enrichment, contact discovery, and search history, so your agent can find prospects, enrich records, discover contact details, and manage saved searches on your behalf.
- People and company discovery: Have your agent search for people or companies using natural language or supported search filters, then review the matching results.
- Contact enrichment: Direct your agent to enrich a person, LinkedIn profile, or company with structured information, including employees when available.
- Email and phone lookup: Let the agent find professional or personal email addresses and phone numbers, or look up people from known email addresses and phone numbers.
- Bulk prospect research: Instruct your agent to start bulk people or company enrichment and batch email or phone discovery jobs, then check their progress and results.
- Search history and exclusions: Have your agent review, favourite, or remove search history entries, manage exclusion lists, and check available search limits and credit balance.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `SIXTYFOUR_AUTOCOMPLETE_SEARCH_FILTER` | Autocomplete Search Filter | Return autocomplete suggestions for one supported people or company search filter field. Queries can contain sensitive targeting criteria such as location, education, job title, industry, language, or technology. This read-only endpoint is limited by Sixtyfour to 200 requests per minute per user. |
| `SIXTYFOUR_CHECK_BALANCE` | Check Balance | Validate the connected API key and return its organization's current Sixtyfour credit balance without consuming credits. This does not identify the connected user. |
| `SIXTYFOUR_CLEAR_SEARCH_HISTORY` | Clear Search History | Permanently delete every search-history entry for the connected Sixtyfour account. This is destructive, affects all saved searches, and cannot be undone. |
| `SIXTYFOUR_CREATE_EXCLUSION_LIST` | Create Exclusion List | Create an immutable, organization-owned people or company exclusion list from an uploaded CSV, inline identifiers, or a saved search. Materialization is asynchronous; poll the returned ID with GET_EXCLUSION_LIST. Sources and saved list state may contain sensitive person or company identifiers. |
| `SIXTYFOUR_DELETE_EXCLUSION_LIST` | Delete Exclusion List | Soft-delete an organization-owned exclusion list and evict its cached member set. This destructive state mutation removes the list from use in searches; verify the list ID before deleting sensitive organization search state. |
| `SIXTYFOUR_DELETE_SEARCH_HISTORY_ENTRY` | Delete Search History Entry | Permanently delete one Sixtyfour search-history entry by ID. This destructive action cannot be undone; use CLEAR_SEARCH_HISTORY only when every entry should be removed. |
| `SIXTYFOUR_ENRICH_COMPANY` | Enrich Company | Synchronously research and enrich one company, optionally finding employees. The documented runtime can be several minutes depending on research depth; use START_COMPANY_ENRICHMENT for production. This billable action costs 0.3/1/5/15 credits at micro/low/medium/high, and high requires provider enablement. Company and employee enrichment may send or return sensitive identities, employment and contact details, profile URLs, source URLs, and evidence. Do not blindly retry after a timeout or ambiguous server error because the request may have been billed. |
| `SIXTYFOUR_ENRICH_LINKEDIN_PROFILE` | Enrich LinkedIn Profile | Fetch one LinkedIn person or company profile and extract structured fields in a single model call. This billable action costs 0.3 credits per profile. It sends a profile URL and may return sensitive personal identifiers, employment details, contact data, profile content, source URLs, and evidence. Do not blindly retry after a timeout or ambiguous server error because the request may have been billed. |
| `SIXTYFOUR_ENRICH_PERSON` | Enrich Person | Synchronously research and enrich one person. The documented runtime is P95 about 5 minutes and can reach 10 minutes, so clients need at least a 15-minute timeout; use START_PEOPLE_ENRICHMENT for production. This billable action costs micro 0.3, low 1, medium 20, high 40, scout 10, or xhigh 250 credits per unit. High, scout, and xhigh require provider enablement and can return 403. It sends and may return sensitive personal identifiers, employment and contact data, profile URLs, source URLs, and evidence. Do not blindly retry after a timeout or ambiguous server error because the request may have been billed. |
| `SIXTYFOUR_EXPORT_SEARCH_RESULTS` | Export Search Results | Start an asynchronous CSV export from exactly one completed search ID or parsed query. The export costs 0.1 credit per result and creates a billable export task. Poll the returned task ID with search status, then request a download URL from the completed task's resource handle. Do not retry this action after a timeout or ambiguous server response because an export may already be running or billed. |
| `SIXTYFOUR_FIND_EMAIL` | Find Email | Synchronously find one person's professional or personal email and return the result in the same call; unlike asynchronous discovery, this action does not start a job or use a webhook. Professional discovery costs 0.5 credits per lead and personal discovery costs 2 credits per lead. This high-sensitivity operation sends personal and company identifiers and may return private contact data and source evidence. Do not blindly retry after a timeout or ambiguous 5xx response because the lookup may have completed and been billed. |
| `SIXTYFOUR_FIND_EMAILS` | Find Emails | Synchronously find professional or personal emails for a batch of leads and return all results in the same call; unlike asynchronous bulk discovery, this action does not start a job or use a webhook. Professional discovery costs 0.5 credits per lead and personal discovery costs 2 credits per lead, so the total cost scales with the number of leads. This high-sensitivity operation sends personal and company identifiers and may return private contact data and source evidence. Do not blindly retry after a timeout or ambiguous 5xx response because the batch may have completed and been billed. |
| `SIXTYFOUR_FIND_PHONE` | Find Phone | Synchronously find one person's phone number and return the result in the same call; unlike asynchronous discovery, this action does not start a job or use a webhook. Discovery costs 3 credits per phone number found. This high-sensitivity operation sends personal identifiers and may return private phone data and source evidence. Do not blindly retry after a timeout or ambiguous 5xx response because the lookup may have completed and been billed. |
| `SIXTYFOUR_FIND_PHONES` | Find Phones | Synchronously find phone numbers for a batch of leads and return all results in the same call; unlike asynchronous bulk discovery, this action does not start a job or use a webhook. Discovery costs 3 credits per phone number found, so the total cost scales with successful discoveries across the batch. This high-sensitivity operation sends personal identifiers and may return private phone data and source evidence. Do not blindly retry after a timeout or ambiguous 5xx response because the batch may have completed and been billed. |
| `SIXTYFOUR_GET_DEEP_SEARCH_STATUS` | Get Deep Search Status | Poll the dedicated deep-search-only status route required for explicit endpoint mapping. For new deep-search workflows, GET_SEARCH_STATUS is the documented general route and also supports export tasks. This route does not support lookalike tasks. Status polling is free and retains normal safe-read retries. |
| `SIXTYFOUR_GET_EXCLUSION_LIST` | Get Exclusion List | Fetch one organization-owned exclusion list, including its materialization status and size. The name, source metadata, counts, and failure detail may describe sensitive people or company records. |
| `SIXTYFOUR_GET_JOB_STATUS` | Get Job Status | Return the current status and, when complete, the task-dependent result for an asynchronous enrichment, email-discovery, or phone-discovery job. Polling is free; poll about every 10 seconds and stop on a terminal status. Completed results may contain sensitive personal identifiers, contact details, employment data, references, and evidence. |
| `SIXTYFOUR_GET_LOOKALIKE_SEARCH_STATUS` | Get Lookalike Search Status | Poll only a task returned by START_LOOKALIKE_SEARCH. The general GET_SEARCH_STATUS route rejects lookalike task IDs. On completion, use search_id with SEARCH_PEOPLE_AND_COMPANIES to page through results. Polling is free and retains normal safe-read retries. |
| `SIXTYFOUR_GET_SEARCH_DOWNLOAD_URL` | Get Search Download URL | Return signed URL metadata for a completed search or export without following or fetching the URL. The signed URL expires after 15 minutes. A subsequent fetch of that URL requires the Sixtyfour x-api-key header, but this action will not forward the connected API key to the returned URL. |
| `SIXTYFOUR_GET_SEARCH_FILTER_CAPABILITIES` | Get Search Filter Capabilities | Return Sixtyfour's current searchable fields, operators, nested paths, query limits, cache metadata, and per-result price for people or company filter search. Use this before constructing provider-native search filters. |
| `SIXTYFOUR_GET_SEARCH_HISTORY_ENTRY` | Get Search History Entry | Retrieve one decrypted saved-search envelope owned by the connected user or active team. The result can contain sensitive search queries, replay metadata, people or company identifiers, exports, and organization-owned search state. Inaccessible IDs are reported as not found. |
| `SIXTYFOUR_GET_SEARCH_HISTORY_VOLUME` | Get Search History Volume | Return search-history volume for a required date-time window. Counts concern sensitive team activity and may reflect saved queries, people or company searches, exports, and organization-owned search state. |
| `SIXTYFOUR_GET_SEARCH_LIMITS` | Get Search Limits | Return the maximum number of search rows the connected credential may request, retrieve, or export. Use this value instead of inferring an entitlement from a plan name. |
| `SIXTYFOUR_GET_SEARCH_STATUS` | Get Search Status | Poll the general status route for a task returned by START_DEEP_SEARCH or a search export. Do not use it for lookalike tasks; use GET_LOOKALIKE_SEARCH_STATUS instead. Polling is free; poll every 10 to 15 seconds and stop on any status other than running. |
| `SIXTYFOUR_LIST_EXCLUSION_LISTS` | List Exclusion Lists | List the connected organization's people and company exclusion lists, most recent first. Returned names, source metadata, counts, and errors are organization-owned search state and may describe sensitive records. |
| `SIXTYFOUR_LIST_SEARCH_FILTER_FIELD_VALUES` | List Search Filter Field Values | Return the most common values for one supported people or company search field, optionally scoped by either simple filters or raw DSL filters. Use filter capabilities first to identify fields that support top values. |
| `SIXTYFOUR_LIST_SEARCH_HISTORY` | List Search History | List one page of the connected team's decrypted saved-search history for logs and auditing. History can contain sensitive queries, people or company records, identifiers, exports, and organization-owned search state. The raw provider object is returned in result; inspect it for provider continuation data and pass any cursor back unchanged. |
| `SIXTYFOUR_LOOK_UP_PEOPLE_BY_EMAILS` | Look Up People by Emails | Synchronously reverse-lookup a batch of people from email addresses. This high-sensitivity operation costs 0.5 credits per lookup, so total cost scales with the number of leads, and may return personal, employment, profile, and contact data. The complete provider JSON response appears in result. Do not blindly retry after a timeout or ambiguous 5xx response because the lookups may already have consumed credits. |
| `SIXTYFOUR_LOOK_UP_PEOPLE_BY_PHONES` | Look Up People by Phones | Synchronously look up people from a batch of phone-number leads and return the results. This sensitive-data operation costs 3 credits per lookup, so total cost scales with the number of leads. Do not blindly retry after a timeout or ambiguous response because lookups may already have consumed credits. |
| `SIXTYFOUR_LOOK_UP_PERSON_BY_EMAIL` | Look Up Person by Email | Synchronously reverse-lookup one person from an email address. This high-sensitivity operation costs 0.5 credits per lookup and may return personal, employment, profile, and contact data. The complete provider JSON response appears in result. Do not blindly retry after a timeout or ambiguous 5xx response because the lookup may already have consumed credits. |
| `SIXTYFOUR_LOOK_UP_PERSON_BY_PHONE` | Look Up Person by Phone | Synchronously look up one person from a phone number and return the result. This sensitive-data operation costs 3 credits per lookup and sends a phone number and other supplied lead details to Sixtyfour. Do not blindly retry after a timeout or ambiguous response because the lookup may already have consumed credits. |
| `SIXTYFOUR_SEARCH_PEOPLE_AND_COMPANIES` | Search People and Companies | Run exactly one page of a people or company search from one query source, or continue using only a prior cursor. Do not loop automatically: Sixtyfour charges 0.1 credit per returned result and each page can incur an additional charge. This read-only action never stores search history. Queries and results may contain people or company records, identifiers, profiles, and organization-owned search state. |
| `SIXTYFOUR_SET_SEARCH_HISTORY_FAVOURITE` | Set Search History Favourite | Set or remove the favourite marker on one Sixtyfour search-history entry. This update is reversible: call it again with the opposite favourite value. |
| `SIXTYFOUR_START_BULK_COMPANY_ENRICHMENT` | Start Bulk Company Enrichment | Upload a CSV, JSON, JSONL, or NDJSON file and start an asynchronous company enrichment job. The provider accepts files up to 100 MB and 100,000 rows; file contents and row count are validated by Sixtyfour. Poll GET_JOB_STATUS with the returned task_id. Per-row base rates are 0.3/1/5/15 credits for micro/low/medium/high; the estimate can undercount find_people and other additions. Inputs and results can contain highly sensitive company, person, employment, contact, profile, source, and evidence data. Set idempotency_key and reuse it when retrying after a timeout or ambiguous 5xx response, because the billable job may already have started. |
| `SIXTYFOUR_START_BULK_EMAIL_DISCOVERY` | Start Bulk Email Discovery | Start asynchronous professional or personal email discovery for a batch of leads. This high-sensitivity operation sends personal and company identifiers to Sixtyfour and may return private contact data and source evidence. Professional discovery costs 0.5 credits per lead and personal discovery costs 2 credits per lead, so total cost scales with the number of leads. The provider response appears in result; take any returned job identifier from there and pass it to SIXTYFOUR_GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous response because a billable job may already have started. |
| `SIXTYFOUR_START_BULK_PEOPLE_ENRICHMENT` | Start Bulk People Enrichment | Upload a CSV, JSON, JSONL, or NDJSON file and start asynchronous people enrichment in bulk. The provider accepts files up to 100 MB and 100,000 rows; file contents and row count are validated by Sixtyfour. Tiers cost micro 0.3, low 1, medium 20, high 40, scout 10, or xhigh 250 credits per unit. High, scout, and xhigh require provider enablement and can return 403. The returned estimate is a floor and the final charge can be higher depending on options and processing. Uploaded rows may contain sensitive personal and contact data; send only data you are authorized to process. Poll SIXTYFOUR_GET_JOB_STATUS with the returned task_id. Supply idempotency_key for retry safety; after a timeout or ambiguous 5xx response, retry only with the same key because a billable job may already have started. |
| `SIXTYFOUR_START_BULK_PHONE_DISCOVERY` | Start Bulk Phone Discovery | Start asynchronous, high-sensitivity phone discovery for a batch of leads. This operation costs 3 credits per phone number found, so the total cost varies with successful discoveries. The provider response appears in result; take any returned job identifier from there and poll SIXTYFOUR_GET_JOB_STATUS with it. Do not blindly retry after a timeout or ambiguous 5xx response because a billable bulk job may already have started. |
| `SIXTYFOUR_START_COMPANY_ENRICHMENT` | Start Company Enrichment | Start an asynchronous company research job and return its task ID for polling. This credit-metered action costs 0.3/1/5/15 credits at micro/low/medium/high; high requires provider enablement. Company and optional employee enrichment may send or return employee identities, employment details, profiles, source URLs, and evidence. Do not blindly retry after a timeout or ambiguous 5xx response because a billable job may already have started. |
| `SIXTYFOUR_START_DEEP_SEARCH` | Start Deep Search | Start an asynchronous agentic people or company search from natural language. Save task_id and poll GET_SEARCH_STATUS, the general route for deep-search and export tasks; GET_DEEP_SEARCH_STATUS is the deep-search-only mapped alternative. On completion, pass search_id to SEARCH_PEOPLE_AND_COMPANIES. Deep Search costs 0.1 credit per result. Reuse a supplied search_id after an ambiguous outcome; without one, determine whether a task started before retrying. |
| `SIXTYFOUR_START_EMAIL_DISCOVERY` | Start Email Discovery | Start an asynchronous search for one person's professional or personal email. This operation is credit-metered: professional discovery costs 0.5 credits per lead and personal discovery costs 2 credits per lead. It sends person identifiers to Sixtyfour and may return private contact data and source evidence. The provider response appears in result; take any returned job identifier from there and pass it to SIXTYFOUR_GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous 5xx response because a billable job may already have started. |
| `SIXTYFOUR_START_LOOKALIKE_SEARCH` | Start Lookalike Search | Start an asynchronous people lookalike search from exactly one seed source. Prefer linkedin_urls for a self-contained call; csv_resource_handle_id requires Sixtyfour's documented upload route, which this toolkit does not expose. Poll only GET_LOOKALIKE_SEARCH_STATUS, then use its search_id with SEARCH_PEOPLE_AND_COMPANIES. This start can consume search credits; the saved pricing documentation does not publish a separate lookalike rate. Do not blindly retry after an ambiguous outcome because a billable task may already have started. |
| `SIXTYFOUR_START_PEOPLE_ENRICHMENT` | Start People Enrichment | Start an asynchronous research job for one person and return a job ID for GET_JOB_STATUS. This operation costs micro 0.3, low 1, medium 20, high 40, scout 10, or xhigh 250 credits per unit. High, scout, and xhigh require provider enablement and can return 403. Requests and results may contain sensitive names, employment data, contact identifiers, profiles, source URLs, and evidence. Supply dispatch_id for retry safety; after a timeout or ambiguous 5xx response, do not retry without the same dispatch_id because a billable job may already have started. |
| `SIXTYFOUR_START_PEOPLE_LOOKUP_BY_EMAILS` | Start People Lookup by Emails | Start asynchronous reverse-email lookup for a batch of people. This high-sensitivity operation costs 0.5 credits per lookup, so total cost scales with the number of leads, and may return personal, employment, profile, and contact data. The provider response appears in result; pass its job identifier to SIXTYFOUR_GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous 5xx response because a billable bulk job may already have started. |
| `SIXTYFOUR_START_PEOPLE_LOOKUP_BY_PHONES` | Start People Lookup by Phones | Start asynchronous lookups of people from a batch of phone-number leads. This sensitive-data operation costs 3 credits per lookup, so total cost scales with the number of leads. The provider response appears in result; pass its returned job identifier to GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous response because a billable bulk job may already have started. |
| `SIXTYFOUR_START_PERSON_LOOKUP_BY_EMAIL` | Start Person Lookup by Email | Start an asynchronous reverse-email lookup for one person. This high-sensitivity operation costs 0.5 credits per lookup and may return personal, employment, profile, and contact data. The provider response appears in result; pass its job identifier to SIXTYFOUR_GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous 5xx response because a billable job may already have started. |
| `SIXTYFOUR_START_PERSON_LOOKUP_BY_PHONE` | Start Person Lookup by Phone | Start an asynchronous lookup of one person from a phone number. This sensitive-data operation costs 3 credits per lookup and sends a phone number and other supplied lead details to Sixtyfour. The provider response appears in result; pass its returned job identifier to GET_JOB_STATUS. Do not blindly retry after a timeout or ambiguous response because a billable job may already have started. |
| `SIXTYFOUR_START_PHONE_DISCOVERY` | Start Phone Discovery | Start an asynchronous search for one person's phone number. This credit-metered operation costs 3 credits per phone number found and sends person identifiers that may lead to private phone data and source evidence. The provider response appears in result; take any returned job identifier from there, pass it to GET_JOB_STATUS, and poll about every 10 seconds. Do not blindly retry after a timeout or ambiguous 5xx response because a billable job may already have started. |
| `SIXTYFOUR_VERIFY_EMAIL` | Verify Email | Check whether one email address can receive mail and return its delivery status and optional 0-100 score. This transmits and evaluates personal contact data. The operation consumes 0.1 Sixtyfour credits unless the result is UNKNOWN; documented 503 failures are also not charged. |

## Supported Triggers

None listed.

## Troubleshooting

### Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

### Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

### Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See [Composio pricing](/pricing/platform) for the current limits that apply to your connection.

## Complete Code

None listed.

## Conclusion

### Use Sixtyfour from Atomic Agent
With your account connected, ask Atomic Agent to work with Sixtyfour in natural language. You can connect more apps through the same Composio integration as you need them.
Visit the [Atomic Agent website](https://atomicagent.io/?cta_placement=atomic-agent-site) or inspect the [Atomic Agent source code](https://github.com/AtomicBot-ai/atomic-agent?cta_placement=atomic-agent-repo).

## How to build Sixtyfour MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/sixtyfour/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/sixtyfour/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/sixtyfour/framework/hermes-agent)

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Autobound](https://composio.dev/toolkits/autobound) - Autobound is an AI-powered sales engagement platform that crafts hyper-personalized outreach and insights. It helps sales teams boost response rates and close more deals through tailored content and recommendations.
- [Better proposals](https://composio.dev/toolkits/better_proposals) - Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.
- [Bidsketch](https://composio.dev/toolkits/bidsketch) - Bidsketch is a proposal software that helps businesses create professional proposals quickly and efficiently. It streamlines the proposal process, saving time while boosting client win rates.
- [Bolna](https://composio.dev/toolkits/bolna) - Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.
- [Botdog](https://composio.dev/toolkits/botdog) - Botdog is a LinkedIn outreach platform for managing campaigns, leads, messages, analytics, and sending accounts. It helps sales teams run outbound workflows and track performance from one place.
- [BotPenguin](https://composio.dev/toolkits/botpenguin) - BotPenguin is an AI chatbot platform for customer messaging, contacts, and conversations. It helps teams manage bot-led support and lead engagement across channels.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Callerapi](https://composio.dev/toolkits/callerapi) - CallerAPI is a white-label caller identification platform for branded caller ID and fraud prevention. It helps businesses boost customer trust while stopping spam, fraud, and robocalls.
- [Callingly](https://composio.dev/toolkits/callingly) - Callingly is a lead response management platform that automates immediate call and text follow-ups with new leads. It helps sales teams boost response speed and close more deals by connecting seamlessly with CRMs and lead sources.
- [Callpage](https://composio.dev/toolkits/callpage) - Callpage is a lead capture platform that lets businesses instantly connect with website visitors via callback. It boosts lead generation and increases your sales conversion rates.
- [Charla](https://composio.dev/toolkits/charla) - Charla is a live chat and AI customer-support platform for property teams. It helps manage guest conversations, property contacts, and support knowledge.
- [Chatforma](https://composio.dev/toolkits/chatforma) - Chatforma is a chatbot automation platform for building and managing bots. It helps teams run dialogs, segments, broadcasts, forms, and user updates from one place.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Crisp](https://composio.dev/toolkits/crisp) - Crisp is a customer messaging platform for live chat, contacts, helpdesk, and campaigns. It helps support teams manage customer conversations from one shared workspace.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Sixtyfour MCP?

With a standalone Sixtyfour MCP server, the agents and LLMs can only access a fixed set of Sixtyfour tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Sixtyfour and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Atomic Agent?

Yes, you can. Atomic Agent fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Sixtyfour tools.

### Can I manage the permissions and scopes for Sixtyfour while using Tool Router?

Yes, absolutely. You can configure which Sixtyfour scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Sixtyfour data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
