Asana MCP Configuration
The Asana MCP configuration provides a hosted JSON schema that connects AI assistants — including Claude Desktop, Cursor, Windsurf, and VS Code Copilot — to the Asana API via the Model Context Protocol. This configuration maps 10 API endpoints as callable tools, including Get attachments from an object, Upload an attachment, Get an attachment, and more. No authentication credentials are needed — it works out of the box. The configuration is auto-generated from the Asana OpenAPI specification (v1.0) and has a quality score of 34/99 (fair documentation coverage). Use the hosted URL below to auto-load this schema into any compatible MCP client.
Quick Specs Reference
Hosted Config URL
Use this hosted URL in any client that supports remote MCP schema auto-loading.
https://mcpbridge.org/config/asana-com.jsonOne-Click Client Setup
Copy the configurations below to wire your local coding assistant directly.
Claude Desktop
claude_desktop_config.json{
"mcpServers": {
"asana-com": {
"command": "npx",
"args": [
"-y",
"@mcp/asana-com"
],
"env": {
"ASANA_API_KEY": "your_asana_api_key"
}
}
}
}Cursor & VS Code
MCP Server URL Setup{
"mcpServers": {
"asana-com": {
"url": "https://mcpbridge.org/config/asana-com.json"
}
}
}Raw Configuration JSON
For local command line wrappers or dynamic shell bindings.
{
"mcpServers": {
"asana-com": {
"command": "npx",
"args": ["-y","@mcp/asana-com"],
"env": {
"ASANA_API_KEY": "your_asana_api_key"
}
}
}
}Required Environment Keys
Substitute these secrets inside your configuration directory environment definitions.
ASANA_API_KEYyour_asana_api_key with your secret key credentialMapped Web APIs & Tools
The following routes will be exposed directly as protocol tools for the LLM.
/attachmentsGet attachments from an object
/attachmentsUpload an attachment
/attachments/{attachment_gid}Get an attachment
/attachments/{attachment_gid}Delete an attachment
/batchSubmit parallel requests
/custom_fieldsCreate a custom field
/custom_fields/{custom_field_gid}Get a custom field
/custom_fields/{custom_field_gid}Update a custom field
/custom_fields/{custom_field_gid}Delete a custom field
/custom_fields/{custom_field_gid}/enum_optionsCreate an enum option
Similar Configurations
GitHub API
Access GitHub repositories, issues, pull requests, and more. Integrate GitHub workflows directly into your AI agent.
https://mcpbridge.org/config/github.jsonGitLab API
Manage repositories, CI/CD pipelines, and merge requests through your AI agent.
https://mcpbridge.org/config/gitlab.jsonBox Platform API
The Box Platform API, provided by Box (box.com), is a robust and comprehensive RESTful service that enables deep integration with the Box cloud content management ecosystem. It serves as the programmatic backbone for enterprises and developers seeking to build custom applications and workflows that interact with content stored securely in Box. Its core capabilities extend far beyond basic file operations, encompassing a full spectrum of content lifecycle management. Developers can programmatically create, upload, download, search, and manage files and folders, but the API's true power lies in its enterprise-grade features. These include advanced collaboration management through invitations and permissions, granular user and group administration within an enterprise directory, and sophisticated security and compliance controls. Specific endpoint groups for managing collaboration whitelists and exempt targets allow for precise governance over external sharing policies, ensuring that content is only shared with approved domains. Furthermore, the API facilitates complex legal and compliance use cases, such as placing items on legal hold or applying retention policies, making it an indispensable tool for regulated industries and large organizations. Exposing this API as tools via the Model Context Protocol (MCP) for AI coding assistants transforms it from a static integration point into a dynamic, conversational development partner. The value lies in delegating repetitive, structured, and context-aware platform operations to the AI agent. Instead of manually writing scripts or navigating multiple dashboard clicks, a developer can instruct the AI to perform precise actions using natural language, which the AI translates into the correct API calls. For instance, an AI assistant equipped with these MCP tools can intelligently query the `GET /collaborations` endpoint to analyze the permission landscape for a sensitive project folder, or it can generate the necessary configuration to programmatically whitelist a new partner domain using `POST /collaboration_whitelist_entries`. This drastically accelerates development and operational workflows, reduces the cognitive load on developers, and minimizes the risk of manual errors in scripting repetitive tasks, effectively embedding the Box Platform's capabilities directly into the developer's AI-augmented workflow. Within this MCP-enabled environment, a developer can instruct the AI agent to perform a variety of powerful, dynamic tasks. For example, a natural language command like, "Set up the standard folder structure for our new 'Project Phoenix' initiative under the Corporate Engineering directory, then add the legal team as collaborators with viewer-only permissions," can be orchestrated by the AI. It would sequentially create the folder hierarchy via the file management endpoints, search for the existing 'Legal' group using the user management APIs, and finally apply the correct permissions using the collaborations endpoint. Another practical workflow involves security auditing; a developer could ask, "List all external collaborations on files within the '2024 Financial Reports' folder and check if any are outside our approved vendor list." The AI agent would query the relevant endpoints, cross-reference the results against the collaboration whitelist entries via `GET /collaboration_whitelist_entries`, and provide a concise report or even take corrective action by revoking specific collaborations if instructed. Critical attention must be paid to authentication and security when implementing this API integration. While the described endpoints use a 'None' authentication method for the initial `GET /authorize` step (which is part of the OAuth 2.0 flow initiation), all subsequent data operations require a valid OAuth 2.0 access token. The principle of least privilege is paramount; developers must configure their applications with the narrowest OAuth scopes necessary for their specific use case, avoiding broad `read_write_all` scopes when `read_only` or scoped write access suffices. All tokens must be stored securely, and refresh tokens should be handled with care. For enterprise deployments, administrators should enable Box's IP whitelisting for API access and mandate two-factor authentication for associated accounts. Furthermore, developers must implement rigorous error handling and leverage Box's comprehensive webhook system for event-driven architectures, rather than relying solely on polling. Finally, all API interactions should be logged for audit trails, especially when managing compliance-related features like legal holds or retention policies, to ensure accountability and support for regulatory requirements.
https://mcpbridge.org/config/box-com.jsonclickup20
The clickup20 Polls API is a lightweight, focused web service designed to facilitate the creation and management of simple polling mechanisms. Provided by ClickUp, a platform known for its project management and productivity tools, this API serves as a specialized component for gathering quick, quantitative feedback. Its core capabilities are straightforward: it allows consumers to programmatically retrieve a list of existing poll questions and to submit new poll questions for consideration. Typical use cases span both enterprise and consumer domains. In an enterprise setting, a development team might integrate this API to run quick polls during sprint retrospectives, gauge internal sentiment on a new tool, or gather binary feedback on proposed technical designs within a project management workflow. For consumer applications, it could power simple feedback widgets within a mobile app or website, enabling users to vote on feature priorities or content topics. The API’s simplicity, requiring no authentication, makes it highly accessible for rapid prototyping and integration into internal tools where complex credential management is unnecessary. Exposing this API as a tool via the Model Context Protocol (MCP) to an AI coding assistant like Claude Desktop, Cursor, or Cline unlocks significant value by transforming static data into a dynamic, interactive resource. The primary value lies in enabling the AI agent to become an active participant in the polling lifecycle, rather than a passive observer. With MCP, the AI can understand the API’s schema and endpoints as callable functions. This allows the assistant to proactively fetch the current state of polls to inform its responses or code suggestions, or to initiate changes based on developer commands. For instance, an AI could be instructed to analyze the results of a poll about preferred coding frameworks and then use that context to suggest project boilerplate code or library imports. This bridges the gap between raw data and actionable intelligence, making the AI a more context-aware and integrated development partner that can manipulate external data sources as part of its reasoning process. Practical workflow examples demonstrate how a developer can leverage this MCP server for dynamic task automation. A developer could instruct the AI agent, “Query all current poll questions and summarize the topics to ensure we haven’t duplicated efforts.” The AI would then use the GET /questions tool to retrieve the data, analyze it, and provide a concise summary. Another powerful workflow involves automating data entry: “Based on the discussion in our last stand-up notes file, create three poll questions to help the team decide on our next tech debt priority.” The AI would parse the notes, formulate appropriate questions, and use the POST /questions tool to create them, significantly reducing manual overhead. Furthermore, an agent could be tasked with maintaining a historical record, such as, “Every Monday at 9 AM, fetch the list of poll questions and append them to a running log in our team’s documentation repository,” creating an automated audit trail without continuous human intervention. Given that the clickup20 API currently operates with no authentication method, developers must exercise extreme caution and implement stringent security best practices at the integration and network layers. While the absence of authentication simplifies setup, it inherently exposes the API to unauthorized access and data manipulation. The principle of least privilege is critical; this API should only be exposed on highly secure, private networks or within isolated development environments. Public exposure must be avoided entirely. Implementing a proxy or gateway that adds an authentication layer (such as API keys, OAuth 2.0, or JWT verification) before forwarding requests to the API is a mandatory mitigation. Developers must also ensure that sensitive data is not included in poll questions and that the API’s functionality is not relied upon for any critical or proprietary decision-making processes. Configuration should involve strict firewall rules and thorough review of any AI agent’s actions to prevent unintended data modification or exfiltration.
https://mcpbridge.org/config/clickup-com.json