intacct-docs
Provides queryable access to Sage Intacct REST API documentation, enabling AI assistants to search endpoints, browse schemas, generate example payloads, and check documentation quality.
Click on "Deploy 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., "@intacct-docs Generate an example payload for creating a vendor."
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.
Sage Intacct Documentation MCP Server
An MCP server that gives AI assistants queryable access to Sage Intacct REST API documentation. Load one or more OpenAPI specs and let your LLM search endpoints, browse schemas, generate example payloads, and check documentation quality — all without leaving the conversation.
Quick Start
1. Install
npm install -g @rowellewis/intacct-docs-mcpOr run without installing:
npx @rowellewis/intacct-docs-mcp2. Add to Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"intacct-docs": {
"command": "npx",
"args": ["-y", "@rowellewis/intacct-docs-mcp"],
"env": {
"SPEC_DIR": "/path/to/your/specs"
}
}
}
}Omit SPEC_DIR to use the bundled Sage Intacct spec.
3. Try it
"Search for endpoints related to accounts payable vendors." "Show me the request body schema for POST /objects/accounts-payable/vendor." "Generate an example payload for creating a journal entry."
Related MCP server: mcp-swagger
Tools
Tool | What it does |
| Fuzzy full-text search across paths, summaries, and descriptions. Supports multi-word queries and typo tolerance. |
| Full documentation for a specific endpoint — parameters, request/response schemas, examples. |
| Schema definition with all properties, types, and constraints. |
| Browse available schema names, filterable by prefix. |
| All API tags/categories with endpoint counts. |
| All endpoints under a specific tag. Use |
| Generates a realistic JSON request body for any endpoint, inferred from its schema. |
| Scores documentation quality (0–100) and lists issues by severity. |
| Readiness status, index counts, and startup timing. |
Full parameter reference, error codes, and examples: docs/public-contract.md.
Configuration
Variable | Default | Description |
|
| Directory scanned for |
|
|
|
|
| Port when using HTTP transport |
|
| Bind address for HTTP transport ( |
|
| Response size cap — output is truncated with a notice when exceeded |
|
|
|
|
| Maximum HTTP request body size in bytes |
|
| Max requests per minute per IP (HTTP transport) |
Development
npm install
npm run build # compile TypeScript
npm run dev # watch mode with tsx
npm test # run all testsNode.js >=18 required.
Project layout:
src/
├── app.ts # tool registry and handlers
├── config.ts # env vars → AppConfig
├── index.ts # entry point, transport selection
├── core/
│ ├── indexer.ts # in-memory indexes + fuzzy search
│ ├── formatter.ts # markdown response formatting
│ ├── fuzzy.ts # trigram similarity matching
│ ├── example-generator.ts
│ ├── validate.ts
│ ├── cache.ts
│ └── spec-quality.ts
└── transport/
├── http-server.ts # MCP Streamable HTTP transport + GET /health
└── stdio.ts # MCP stdio wrapperTests use Vitest.
Deployment
HTTP transport (MCP Streamable HTTP — for URL-based MCP clients):
TRANSPORT=http HTTP_PORT=3000 npm startOperations
Health: call the
healthtool — returns readiness, index counts, and startup duration. Or hitGET /healthwhen running in HTTP mode.Logs: structured JSON on stderr. Adjust verbosity with
LOG_LEVEL.Runbook:
docs/ops-runbook.md
Troubleshooting
Server won't start — verify SPEC_DIR contains at least one *.openapi.yaml file, then run npm run build and check stderr.
Endpoint not found — use search-endpoints to discover paths. Methods must be uppercase (GET, POST, …).
Schema not found — use list-schemas with an optional prefix to browse what's available. Names are case-sensitive.
License
MIT
Available Tools
9 toolsgenerate-exampleA
Generate an example JSON request body for an API endpoint. Example: method="POST", path="/objects/accounts-payable/vendor"
Inputs: path (required), method (required).
get-endpoint-docsA
Get complete documentation for a specific API endpoint including parameters, request/response schemas, and examples. Example: method=GET, path=/objects/general-ledger/account/{key}
Inputs: path (required), method (required).
get-endpoints-by-tagA
Get all API endpoints for a specific tag/category. Use list-tags first to see available tags. Example: tag="Accounts Payable"
Inputs: tag (required).
get-schemaA
Get detailed schema definition including all properties, types, and constraints. Example: schemaName=general-ledger-account
Inputs: schemaName (required).
healthA
Report readiness status and index statistics. Useful for readiness probes.
Inputs: no named parameters.
list-schemasB
List all available schema names, optionally filtered by prefix. Example: prefix="general-ledger"
Inputs: spec, limit, prefix.
list-tagsA
List all API tags/categories with endpoint counts.
Inputs: spec.
search-endpointsA
Search for API endpoints by path, operation ID, summary, or description keywords. Supports fuzzy matching and multi-word queries. Example: query="create invoice" limit=5
Inputs: query (required), spec, limit.
spec-quality-reportC
Analyze OpenAPI spec documentation quality. Returns a score and list of issues.
Inputs: spec, limit, severity.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool has a distinct focus: endpoint docs, endpoint search, schema retrieval, tag/schema listings, example generation, health, and spec quality. There is minor overlap between search-endpoints and get-endpoints-by-tag, and between get-endpoint-docs and generate-example, but descriptions make the differences clear.
Most tool names consistently follow a verb_noun pattern with lowercase hyphenation, such as get-endpoint-docs, list-tags, and search-endpoints. A few exceptions like health and spec-quality-report break the pattern slightly, but the overall style is predictable and readable.
Nine tools is an appropriate size for a documentation server. The toolset covers discovery, retrieval, schema access, example generation, and operational health without feeling bloated or sparse.
The toolset provides a complete workflow for API documentation consumers: discovering endpoints, retrieving endpoint details, exploring schemas, listing categories, and generating examples. The addition of health and spec-quality-report tools extends the surface sensibly rather than leaving obvious gaps.
Maintenance
Related MCP Connectors
Publish your API docs so AI assistants can look up endpoints and call your API correctly.
Discover, compare, route, and execute machine-accessible capabilities for AI agents.
Access and search Branch's official API documentation directly within any AI agent or client.
Connect assistants to your workspace knowledge, skills, and work tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to discover, search, and interact with REST APIs by parsing OpenAPI/Swagger specifications with intelligent fuzzy search across endpoints, supporting both local and remote API sources.5 npm2MIT
- AlicenseAqualityDmaintenanceExposes Swagger/OpenAPI API documentation to AI models, enabling exploration, search, and interaction with endpoints, schemas, and execution of API calls.1413 npm2MIT
- FlicenseNot gradedqualityDmaintenanceBrings OpenAPI/Swagger documentation into AI assistants, enabling endpoint discovery, deep inspection, cURL generation, and TypeScript type generation.-
- AlicenseAqualityDmaintenanceEnables AI assistants to understand and interact with OpenAPI specifications, providing deep insight into API structures for faster and more accurate API integration.918 npm1MIT