OpenAPI SchemaSAFE
OpenAPI Schema Model Context Protocol Server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that exposes OpenAPI schema information to Large Language Models (LLMs) like Claude. This server allows an LLM to explore and understand OpenAPI specifications through a set of specialized tools.
Features
- Load any OpenAPI schema file (JSON or YAML) specified via command line argument
- Explore API paths, operations, parameters, and schemas
- View detailed request and response schemas
- Look up component definitions and examples
- Search across the entire API specification
- Get responses in YAML format for better LLM comprehension
Usage
Command Line
Run the MCP server with a specific schema file:
# Use the default openapi.yaml in current directory npx -y mcp-openapi-schema # Use a specific schema file (relative path) npx -y mcp-openapi-schema ../petstore.json # Use a specific schema file (absolute path) npx -y mcp-openapi-schema /absolute/path/to/api-spec.yaml # Show help npx -y mcp-openapi-schema --help
Claude Desktop Integration
To use this MCP server with Claude Desktop, edit your claude_desktop_config.json configuration file:
{
"mcpServers": {
"OpenAPI Schema": {
"command": "npx",
"args": ["-y", "mcp-openapi-schema", "/ABSOLUTE/PATH/TO/openapi.yaml"]
}
}
}Location of the configuration file:
- macOS/Linux:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
$env:AppData\Claude\claude_desktop_config.json
Claude Code Integration
To use this MCP server with Claude Code CLI, follow these steps:
- Add the OpenAPI Schema MCP server to Claude Code
# Basic syntax claude mcp add openapi-schema npx -y mcp-openapi-schema # Example with specific schema claude mcp add petstore-api npx -y mcp-openapi-schema ~/Projects/petstore.yaml
- Verify the MCP server is registered
# List all configured servers claude mcp list #
dc8e7f38bd7aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-openapi-schema -- npx -y [email protected]
{
"mcpServers": {
"mcp-openapi-schema": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (10)
10 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get-component | read | Gets detailed definition for a specific component |
get-endpoint | read | Gets detailed information about a specific API endpoint |
get-examples | read | Gets examples for a specific component or endpoint |
get-path-parameters | read | Gets the parameters for a specific path |
get-request-body | read | Gets the request body schema for a specific endpoint |
get-response-schema | read | Gets the response schema for a specific endpoint, method, and status code |
list-components | read | Lists all schema components (schemas, parameters, responses, etc.) |
list-endpoints | read | Lists all API paths and their HTTP methods with summaries, organized by path |
list-security-schemes | read | Lists all available security schemes |
search-schema | read | Searches across paths, operations, and schemas |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@apidevtools/swagger-parser, @modelcontextprotocol/sdk, js-yaml, zod
Gates applied: no_behavioural_pass, no_license.
dc8e7f38bd7afull audit observations/trust-audit/mcp-server/hannesj__openapi-schema.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | dc8e7f38bd7a | SAFE | B | 89 | first audit |
Questions
What is the OpenAPI Schema MCP server?
OpenAPI Schema Model Context Protocol Server
What tools does OpenAPI Schema expose?
10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OpenAPI Schema safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does OpenAPI Schema need?
No credential environment variables were found in its source, so it appears to need none.
How does OpenAPI Schema run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-openapi-schema at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (dc8e7f38bd7a), read on 2026-10-08. The repository is watched and re-audited when it changes.