dust-mcp-server
Create and register new MCP servers in Dust to connect remote platforms, using a structured step-by-step development process.
Install
mkdir -p .claude/skills/dust-mcp-server && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4233" && unzip -o skill.zip -d .claude/skills/dust-mcp-server && rm skill.zipInstalls to .claude/skills/dust-mcp-server
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Step-by-step guide for creating new internal MCP server integrations in Dust that connect to remote platforms (Jira, HubSpot, Salesforce, etc.). Use when adding a new MCP server, implementing a platform integration, or connecting Dust to a new external service.Key capabilities
- →Create internal MCP server metadata
- →Implement tool handlers for remote platforms
- →Register servers in the Dust ecosystem
- →Configure OAuth providers for external services
How it works
The process involves creating metadata and handler files within the Dust repository structure, then registering the server in the central constants and index files.
Inputs & outputs
When to use dust-mcp-server
- →Add new platform integration
- →Register internal MCP server
- →Define tool metadata for external services
About this skill
MCP Server Runbook: Adding Internal MCP Server Integrations for Remote Platforms
This runbook provides step-by-step instructions for creating new internal MCP server integrations in Dust that connect to remote platforms (e.g., Jira, HubSpot, Salesforce, etc.).
MVP Fast Path
For a minimal new server (no OAuth, no external API yet — just the skeleton to register and test):
- Create
front/lib/api/actions/servers/{provider}/metadata.tswith a literal metadata array - Create
front/lib/api/actions/servers/{provider}/tools/index.tswith stub handlers - Create
front/lib/api/actions/servers/{provider}/index.tswithcreateServer - Register in
constants.tsandservers/index.ts - Add the server to
SERVER_SOURCESinbm25_tool_search_utils.test.ts - Add at least one BM25 query case to
bm25_tool_search.test.ts
See the BM25 Tests section below for the test setup. This gives you a runnable skeleton with type-checked tool descriptions before writing any real API calls.
Quick Reference
File Structure
front/lib/api/actions/servers/{provider}/
├── metadata.ts # Tool metadata array and server info
├── tools/index.ts # Schema-inferred handlers and built tools
├── index.ts # Provider-local server creation and registration
├── client.ts # API client (optional)
└── helpers.ts # Helper functions (optional)
Registration Files
front/lib/actions/mcp_internal_actions/constants.ts- Add server config withmetadata: YOUR_SERVERfront/lib/actions/mcp_internal_actions/servers/index.ts- Import and register in switch statement
OAuth Requirements (if the platform requires OAuth)
- OAuth provider must already exist in
front/lib/api/oauth/providers/{provider}.ts - OAuth core implementation must exist in
core/src/oauth/providers/{provider}.rs - OAuth scopes must be configured for the required API access
- Server's
authorizationfield must reference the OAuth provider
Common Gotchas
- Do not forget to add the server to
AVAILABLE_INTERNAL_MCP_SERVER_NAMESarray - Server IDs must be stable and unique; never change them once deployed
- Tool stakes must be configured appropriately (
never_ask,low,medium,high) - Every internal tool must define
displayLabels,toolCostCategory, andfreeUsage - Tool descriptions should start with a bare infinitive/base verb like
List,Get,Search,Create, orUpdate - Always implement proper error handling with
Resulttypes - Handle OAuth token refresh automatically through the
withAuthpattern
Prerequisites
OAuth Configuration (if required)
If the remote platform requires OAuth authentication:
- Check whether an OAuth provider exists in
core/src/oauth/providers/as{provider}.rs - Check whether a front OAuth provider exists in
front/lib/api/oauth/providers/{provider}.ts
If the OAuth provider does not exist, implement it first in core and front:
- create
core/src/oauth/providers/{provider}.rs - implement the OAuth flow: authorization URL, token exchange, refresh
- register the provider in
core/src/oauth/providers/mod.rs - create
front/lib/api/oauth/providers/{provider}.tsfor the front-end OAuth setup
See existing providers like hubspot.rs or jira.rs for reference implementations.
Research Phase
Before starting implementation, research the platform API:
1. API Documentation
- find the official API documentation
- identify REST endpoints vs GraphQL vs SDK usage
- note rate limits and pagination requirements
2. Authentication Method
- OAuth 2.0, preferred for user-facing integrations
- API key / bearer token, simpler but less secure
- required OAuth scopes
3. Available Operations
Document the operations you want to expose:
- read operations: list, get, search
- write operations: create, update, delete
- special operations: transitions, associations, etc.
Step-by-Step Implementation
1. Create metadata.ts
Create front/lib/api/actions/servers/{provider}/metadata.ts:
import type { ServerMetadata } from "@app/lib/actions/mcp_internal_actions/tool_definition";
import { z } from "zod";
export const YOUR_PROVIDER_SERVER_NAME = "your_provider" as const;
export const YOUR_PROVIDER_TOOLS_METADATA = [
{
name: "list_items",
description: "List all items accessible to the user.",
schema: {
pageToken: z.string().optional().describe("Page token for pagination."),
maxResults: z.number().optional().describe("Maximum results to return."),
},
stake: "never_ask",
toolCostCategory: "advanced",
freeUsage: false,
displayLabels: {
running: "Listing Items",
done: "List items",
},
},
{
name: "get_item",
description: "Get a single item by ID.",
schema: {
itemId: z.string().describe("The ID of the item to retrieve."),
},
stake: "never_ask",
toolCostCategory: "advanced",
freeUsage: false,
displayLabels: {
running: "Retrieving item",
done: "Retrieve item",
},
},
{
name: "create_item",
description: "Create a new item.",
schema: {
name: z.string().describe("Name of the item."),
description: z.string().optional().describe("Description of the item."),
},
stake: "low",
toolCostCategory: "advanced",
freeUsage: false,
displayLabels: {
running: "Creating item",
done: "Create item",
},
},
] as const;
export const YOUR_PROVIDER_SERVER = {
serverInfo: {
name: YOUR_PROVIDER_SERVER_NAME,
version: "1.0.0",
description: "Short description of what this integration does.",
authorization: {
provider: "your_provider",
supported_use_cases: ["personal_actions", "platform_actions"],
},
icon: "YourProviderLogo",
documentationUrl: "https://docs.dust.tt/docs/your-provider",
instructions: null,
},
tools: YOUR_PROVIDER_TOOLS_METADATA,
} as const satisfies ServerMetadata;
Key points:
- Use
snake_casefor the tool names - Internal tools must include
displayLabels; unlike remote MCP tools, these labels are required - Set
toolCostCategoryandfreeUsagedeliberately, following a comparable existing server - tool descriptions start with a bare infinitive/base verb such as
List,Get,Search,Create,Update, orRetrieve; avoid noun phrases, articles, gerunds, and third-person verbs because descriptions are part of the BM25 tool-search corpus (see BM25-Friendly Descriptions below) stakevalues map to review/approval expectations
BM25-Friendly Descriptions (MCP3 rule)
Tool names and descriptions both drive BM25 retrieval. Names are the strongest signal — they
must be consistent and follow the verb_noun convention (e.g., list_warehouses, get_workbook).
Descriptions are the secondary signal: write each one as if answering "what user intent does this
tool serve?"
Rules:
- Start with a bare infinitive verb:
List,Get,Search,Create,Update,Send,Delete - Include platform-specific nouns that users mention in queries:
warehouse,workbook,ticket,channel - Include common synonyms inline when the platform uses an unusual term:
worksheets (sheets/tabs) - Include the platform name when it adds specificity (e.g.,
Databricks workspace,Excel workbook), but don't lead with the full brand name or repeat it redundantly across every tool - For platform-specific servers, avoid adding location qualifiers (e.g.,
in OneDrive,in SharePoint) to every tool — BM25 treats these as content tokens, so they widen the match surface and cause your tools to surface on location-based queries (e.g., a Drive search) even when the user intended a different tool
Examples:
// BAD — noun phrase, redundant "Microsoft Excel", location noise
description: "Microsoft Excel file listing from OneDrive and SharePoint."
// BAD — gerund
description: "Listing all SQL warehouses in Databricks."
// BAD — third-person verb
description: "Lists all SQL warehouses available in Databricks."
// GOOD — bare infinitive, platform noun, no location noise
description: "List all SQL warehouses available in the Databricks workspace."
// GOOD — synonym in parentheses helps BM25 match "sheets" and "tabs"
description: "Get a list of all worksheets (sheets/tabs) in an Excel workbook."
// GOOD — verb + context + common synonyms
description: "Search Slack channels, messages, and threads by keyword or topic."
Test your descriptions: add a BM25 query case (see next section) before merging. If your expected tool doesn't score > 0 in its own server-scoped index, the description is too generic or missing the key tokens the user will type.
2. Create tools/index.ts
Create front/lib/api/actions/servers/{provider}/tools/index.ts:
import { MCPError } from "@app/lib/actions/mcp_errors";
import type { ToolHandlers } from "@app/lib/actions/mcp_internal_actions/tool_definition";
import { buildTools } from "@app/lib/actions/mcp_internal_actions/tool_definition";
import { YOUR_PROVIDER_TOOLS_METADATA } from "@app/lib/api/actions/servers/your_provider/metadata";
import { Err, Ok } from "@app/types/shared/result";
const handlers: ToolHandlers<typeof YOUR_PROVIDER_TOOLS_METADATA> = {
list_items: async ({ pageToken, maxResults }, { authInfo }) => {
const token = authInfo?.token;
if (!token) {
return new Err(new MCPError("No access token provided"));
}
try {
const items = [];
return new Ok([
{ type: "text" as const, text: `Found ${items.length} items` },
{ type: "text" as const, text: JSON.stringify({ items }, null, 2) },
]);
} catch (e) {
return new Err(new MCPError("Failed to list items"));
}
},
get_item: async ({ itemId }, { authInfo }) => {
const token = authInfo?.token;
if (!token) {
return new Err(new MCPError
---
*Content truncated.*
When not to use it
- →Developing external-facing public MCP servers
- →General platform integration without Dust ecosystem requirements
Prerequisites
Limitations
- →Server IDs must be stable and unique once deployed
- →Requires manual registration in multiple configuration files
- →OAuth token refresh must follow the withAuth pattern
How it compares
This workflow enforces a specific file structure and type-checked tool definition pattern compared to generic MCP server development.
Compared to similar skills
dust-mcp-server side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dust-mcp-server (this skill) | 1 | 25d | Review | Advanced |
| mcporter | 7 | 2mo | No flags | Intermediate |
| calcom-api | 2 | 3mo | No flags | Intermediate |
| developing-genkit-tooling | 2 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by dust-tt
View all by dust-tt →You might also like
mcporter
openclaw
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
calcom-api
calcom
Interact with the Cal.com API v2 to manage scheduling, bookings, event types, availability, and calendars. Use this skill when building integrations that need to create or manage bookings, check availability, configure event types, or sync calendars with Cal.com's scheduling infrastructure.
developing-genkit-tooling
firebase
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.
juicebox-rate-limits
jeremylongshore
Implement Juicebox rate limiting and backoff. Use when handling API quotas, implementing retry logic, or optimizing request throughput. Trigger with phrases like "juicebox rate limit", "juicebox quota", "juicebox throttling", "juicebox backoff".
clay-sdk-patterns
jeremylongshore
Apply production-ready Clay SDK patterns for TypeScript and Python. Use when implementing Clay integrations, refactoring SDK usage, or establishing team coding standards for Clay. Trigger with phrases like "clay SDK patterns", "clay best practices", "clay code patterns", "idiomatic clay".
vercel-sdk-patterns
jeremylongshore
Execute apply production-ready Vercel SDK patterns for TypeScript and Python. Use when implementing Vercel integrations, refactoring SDK usage, or establishing team coding standards for Vercel. Trigger with phrases like "vercel SDK patterns", "vercel best practices", "vercel code patterns", "idiomatic vercel".