# How to integrate Plaid MCP with Hermes

```json
{
  "title": "How to integrate Plaid MCP with Hermes",
  "toolkit": "Plaid MCP",
  "toolkit_slug": "plaid_mcp",
  "framework": "Hermes",
  "framework_slug": "hermes-agent",
  "url": "https://composio.dev/toolkits/plaid_mcp/framework/hermes-agent",
  "markdown_url": "https://composio.dev/toolkits/plaid_mcp/framework/hermes-agent.md",
  "updated_at": "2026-09-06T05:34:01.970Z"
}
```

## Introduction

Hermes is a 24/7 autonomous agent that lives on your computer or server — it remembers what it learns and evolves as your usage grows.
This guide explains the easiest and most robust way to connect your Plaid account to Hermes. You can do this through either Composio Connect CLI or Composio Connect MCP. For personal use we recommend the CLI, but you won't go wrong with MCP either.

## Also integrate Plaid MCP with

- [ChatGPT Work](https://composio.dev/toolkits/plaid_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/plaid_mcp/framework/claude-cowork)

## TL;DR

### What is Composio Connect?
Composio Connect is a consumer offering that lets anyone plug 1,500+ applications directly into their agent harness — including Hermes. It can:
- Search and load tools from relevant toolkits on-demand, reducing context usage.
- Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
- Manage app authentication end-to-end with zero manual overhead.

## Connect Plaid MCP to Hermes

### Integrating Plaid with Hermes
### Using Composio Connect CLI
1. Install the Composio CLI
Run the install script directly, or paste https://composio.dev/hermes into your Hermes chat box to have it installed for you.

```bash
curl -fsSL https://composio.dev/install | bash
```

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

The Plaid MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Plaid account. It provides structured and secure access so your agent can perform Plaid operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PLAID_MCP_PLAID_DEBUG_ITEM` | Plaid debug item | Diagnose a Plaid item by retrieving its state information. This tool provides comprehensive information about why an item may not be working properly. Use this tool when you need to diagnose why an item is not functioning as expected In the response, you will see the following information: 1. Item State: - "Never extracted": no extraction has been attempted for this item yet - "Successful": The most recent extraction was successful - "Retrying": The most recent extraction encountered a temporary issue and is being retried - "Needs user attention": The item requires user input and client access is not permitted - "Needs user attention (with access)": The item requires user input but client access is permitted 2. Item Consent State: - Boolean indicating whether the item has active user consent - If an item is not consented, it cannot perform extractions or updates 3. Item Deleted At: - If set to a non-zero value, indicates when the item was deleted - Deleted items cannot retrieve data, and cannot be patched as it is requested by the end users - If the item is not deleted yet, the response will be "not available" 4. Known Issues: - Includes description and status of any known issues affecting the item - May provide insights into ongoing problems with the connection When diagnosing an item, follow this sequence: - First, check if the item is deleted. If yes, the item cannot work properly. - Second, if the item is not deleted but lacks active consent, it cannot function properly. - Third, if the item is not deleted: * Check item state. If it indicates the item needs user attention, the item requires manual intervention. * Note any known issues as supplementary information, though these are usually not the primary cause of problems. - If all diagnostics look normal but the user still reports issues, advise them to contact Plaid support. - If an item is deleted, it is not working properly. It is not patchable, you should suggest the user to create a new item. - If an item is missing active consent, it is not working properly. You should suggest the user to use Update Mode to reauthorize the item. - If an item state indicates it needs user attention, the user should use Update Mode to reauthorize the item. - If running into error "the item does not belong to the team", it means the item is not associated with the team. You must inform the user that the item does not belong to their selected team. You may ask if they would like to try other teams associated with their account, but do not automatically attempt other teams. - If an item cannot be found, it's possible the item is not in the Production environment. When explaining the error, inform the user that this is a possible reason for the error. |
| `PLAID_MCP_PLAID_GET_LINK_ANALYTICS` | Plaid get link analytics | Retrieves Plaid Link analytics data for analyzing user conversion and error rates. Use this tool when you need to: - Analyze Link conversion funnel metrics - Track user progression through the Link flow - Monitor error rates over time - Evaluate Link performance and user experience Some common use cases: - Monitoring Link conversion rates and identifying drop-offs - Analyzing conversion trends over specific time periods - Tracking error patterns and frequency (both by type and total via CountEntities) - Generating comprehensive Link performance reports - Comparing performance across different stages of the Link flow The response includes three main components: 1. Funnel Data (funnel): Tracks user progression through key Link stages with counts: - countAtLinkOpen: Number of users who opened Link - countAtSelectInstitution: Number who selected an institution - countAtHandoff: Number who completed the handoff process 2. Conversion Over Time (conversionOverTime): Time series data showing conversion trends with: - start: Timestamp marking the start of the series - series: Array of named data series, where each contains: * name: Identifier for the conversion metric * data: Array of counts, can contain null values 3. Errors Over Time (errorsOverTime): Time series tracking error occurrences with: - start: Timestamp marking the start of the series - series: Array of named data series, where each contains: * name: Error type identifier (includes "CountEntities" series for total errors across all types) * data: Array of error counts - If user does not provide a date range, please ask them to provide one. You could ask if they want to see the data for the last 30 days and you could use the current date as the end date. Note that the earliest date available for Link analytics data is September 1, 2023 (9/1/2023). |
| `PLAID_MCP_PLAID_GET_TOOLS_INTRODUCTION` | Plaid get tools introduction | Returns a list of all available tools with a brief introduction for each. Use this tool when users ask questions like "What is this Plaid MCP Server?" or "What tools are available?". Your response should follow this format: This is an official Plaid MCP Server made by Plaid. It provides the following functionalities: * - * - ... |
| `PLAID_MCP_PLAID_GET_USAGES` | Plaid get usages | Retrieves usage metrics for Plaid products and services. Use this tool when you need to: - Get usage data for specific metrics over a time period - Track product usage and consumption - Monitor API request volumes - Generate usage reports for billing purposes The data shows how many times each Plaid product was used within the specified date range for certain metrics, with results aggregated by day. Common metrics include number of API calls, authentication requests, and other product-specific usage counts. The key is the product name, and the value is the list of metric types corresponding to that product. - Auth: ["auth-request", "auth-unverified-request"] - Balance: "balance-request" - Identity: ["identity-request", "identity-match-request"] - Transactions: ["transactions", "transactions-add", "transactions-remove", "transactions-active", "transactions-refresh"] - Investments: ["investments-h-add", "investments-h", "investments-h-remove", "investments-h-active", "investments-t-add", "investments-t", "investments-t-remove", "investments-t-active"] - Investments Move: "investments-auth-request" - Liabilities: ["liabilities-add", "liabilities-remove", "liabilities-active", "liabilities"] - Assets: ["assets-add", "assets-pdf-request", "assets-refresh", "assets-refresh-monthly", "assets-audit-request", "assets-history-request"] - Payments: "payment_initiation-initd" - Enrich: "enriched-transaction" - Signal: "momo-frs-eval-request" - Income: ["income-bank-request", "income-bank-refresh", "income-payroll-request", "income-payroll-refresh", "income-document-request", "income-document-parsing", "income-doc-bank-statemnt", "income-document-fraud"] - Statements: "statements-single-doc" - Identity Verification: ["idv-base", "idv-lightning-group-1", "idv-lightning-group-2", "idv-lightning-group-3", "idv-document", "idv-selfie-check"] - Consumer Report: ["cra-bank-income-request", "cra-base-report-create", "cra-base-report-refresh", "cra-network-insights-req", "income-insights-refresh", "partner-prism-attrib", "partner-prism-scores"] - Monitor: ["monitor-wl-rescan-add", "monitor-wl-rescan-remove", "monitor-wl-base"] - Hosted Link Delivery: ["hosted-link-delivery-eml", "hosted-link-delivery-sms"] - Transfer: ["momo-transfer-ach", "momo-transfer-ach-sd", "momo-wire-request", "momo-rtp-request", "momo-transfer-g-ach", "momo-transfer-g-ach-sd", "momo-transfer-authorized", "momo-transfer-manual-req", "momo-transfer-return-unauthorized", "momo-transfer-return-noc", "momo-transfer-return-other"] - If a user asks for a product similar to one on this list and you're 99% confident it's the same product, query for the product on this list and inform them which product you're querying for. Otherwise, do not query an unrelated product. - "momo-frs-eval-request" is the metric type used in the API for Signal. When communicating with users, refer to it as "signal-request" instead. User: "I want to see the usage data for Transactions" Reasoning: The metric types for Transactions are ["transactions", "transactions-add", "transactions-remove", "transactions-active", "transactions-refresh"]. Input parameters: { "metric_types": ["transactions", "transactions-add", "transactions-remove", "transactions-active", "transactions-refresh"], // other fields ... } User: "What metrics are available for Identity Verification?" Response: We support the following metrics for Identity Verification: idv-base, idv-lightning-group-1, idv-lightning-group-2, idv-lightning-group-3, idv-document, idv-selfie-check. - If metric_types aren't provided, use "auth-request" as the default - If no date range is provided, ask the user for one (suggest last 30 days with current date as end date) - The maximum look-back period is limited to 1 year from the current date |
| `PLAID_MCP_PLAID_LIST_TEAMS` | Plaid list teams | Retrieve teams associated with the user and present them as a selectable list. After the user selects a team, capture the team_id of the selected team for use in subsequent tool requests. 1. You MUST return a numbered list of teams with their names clearly displayed in a human readable format in the conversation dialog - Format each team as: "{number}. {company name} (ID: {team_id})" - Example: "1. XXX Corporation (ID: fakeid00000000000000000)" 2. Ask the user explicitly to select a team by providing either: - The number from the list (e.g., "Please select team 3") - The exact team name (e.g., "I want to use XXX Corporation") - The team ID directly (e.g., "Use team fakeid00000000000000000") 3. After user selection, confirm their choice with a clear acknowledgment: - "You've selected: {company name} (ID: {team_id})" 4. Store and use this team_id for ALL subsequent tool requests that require a team_id parameter 5. Handle edge cases appropriately: - If only one team exists, auto-select it and confirm the selection - If no teams exist, clearly communicate this limitation to the user - If the response is empty, the user is not a member of any teams. Inform the user that they should visit dashboard.plaid.com to join or create a team. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Plaid MCP server provides comprehensive access to Plaid operations through Composio. Once connected, Hermes can perform all major Plaid actions on your behalf using natural language commands.

## Complete Code

None listed.

## Conclusion

### Way Forward
With Plaid connected, Hermes can now act on your behalf whenever it detects a relevant task or you ask it to.
From here, you can extend Hermes further:
- Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Hermes can do for you.
- Build workflows across tools: Once multiple apps are connected, Hermes can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
- Let it learn your patterns: The more you use Hermes, the better it gets at anticipating how you'd handle recurring tasks. Give it feedback on drafts and decisions, and it will adapt.
If you run into trouble or want to share what you've built, join the [community](https://discord.com/invite/composio) or check out the [Docs](https://docs.composio.dev?utm_source=toolkits&utm_medium=framework_template&utm_campaign=hermes&utm_content=docs) for deeper configuration options.

## How to build Plaid MCP Agent with another framework

- [ChatGPT Work](https://composio.dev/toolkits/plaid_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/plaid_mcp/framework/claude-cowork)

## Related Toolkits

- [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
- [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
- [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.
- [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
- [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data.
- [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds.
- [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights.
- [Ahrefs MCP](https://composio.dev/toolkits/ahrefs_mcp) - Ahrefs MCP is Ahrefs' hosted MCP server for SEO data and insights. Use it to access backlinks, organic metrics, keyword research, and competitor analysis.
- [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly.
- [Audioscrape MCP](https://composio.dev/toolkits/audioscrape_mcp) - Audioscrape MCP lets agents search and retrieve speaker-attributed audio, transcripts, entities, and citations from public and workspace content. Use it to surface searchable, speaker-labeled audio and rich metadata for research, meetings, and content discovery.
- [Baremetrics](https://composio.dev/toolkits/baremetrics) - Baremetrics is a subscription analytics platform for recurring-revenue businesses. It helps teams track MRR, churn, customers, and revenue trends in one place.
- [Bing Webmaster Tools](https://composio.dev/toolkits/bing_webmaster_tools) - Bing Webmaster Tools is Microsoft's search console for site performance, crawling, indexing, URL submission, and verified site management. It helps site owners understand Bing Search visibility and fix issues that affect organic traffic.
- [Bread & Butter](https://composio.dev/toolkits/bread_butter) - Bread & Butter is a lead-intelligence and identity platform for website visitor tracking, user profiles, attribution, authentication, and conversion workflows. It helps teams understand who is visiting, where leads come from, and how users convert.
- [Bright Data MCP](https://composio.dev/toolkits/brightdata_mcp) - Bright Data MCP is an AI-powered web scraping and data collection platform. Instantly access public web data in real time with advanced scraping tools.
- [Browseai](https://composio.dev/toolkits/browseai) - Browseai is a web automation and data extraction platform that turns any website into an API. It's perfect for monitoring websites and retrieving structured data without manual scraping.
- [BSC Designer](https://composio.dev/toolkits/bsc_designer) - BSC Designer is a strategy execution platform for balanced scorecards, KPIs, dashboards, and strategy maps. It helps teams turn goals into measurable performance plans they can track over time.
- [Chameleon](https://composio.dev/toolkits/chameleon) - Chameleon is a product adoption platform for building in-app experiences, managing customer data, and analyzing user engagement. It helps teams improve onboarding, feature discovery, and product adoption with targeted user experiences.
- [Chartly](https://composio.dev/toolkits/chartly) - Chartly renders Chart.js configurations as PNG or SVG images and creates permanent chart URLs for sharing and embedding. Share and embed charts easily with stable image URLs and downloadable vector graphics.
- [ChartMogul](https://composio.dev/toolkits/chartmogul) - ChartMogul is a subscription analytics and revenue data platform. It helps teams monitor MRR, churn, customer segments, and billing metrics.
- [ClickHouse](https://composio.dev/toolkits/clickhouse) - ClickHouse is an open-source, column-oriented database for real-time analytics and big data processing using SQL. Its lightning-fast query performance makes it ideal for handling large datasets and delivering instant insights.

## Frequently Asked Questions

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

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

### Can I use Tool Router MCP with Hermes?

Yes, you can. Hermes 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 Plaid tools.

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

Yes, absolutely. You can configure which Plaid 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 Plaid data and credentials are handled as safely as possible.

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