HALSAFE
HAL (HTTP API Layer) is a Model Context Protocol (MCP) server that provides HTTP API capabilities to Large Language Models.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://lobehub.com/mcp/deanward-hal)
HAL is a Model Context Protocol (MCP) server that provides HTTP API capabilities to Large Language Models. It allows LLMs to make HTTP requests and interact with web APIs through a secure, controlled interface. HAL can also automatically generate tools from OpenAPI/Swagger specifications for seamless API integration.
Documentation
[Complete Documentation →](https://deanward.github.io/HAL/documentation/)
Visit our comprehensive documentation site for detailed guides, examples, and API reference.
Features
- HTTP GET/POST/PUT/PATCH/DELETE/OPTIONS/HEAD Requests: Fetch and send data to any HTTP endpoint
- Secure Secret Management: Environment-based secrets with
{secrets.key}substitution and automatic redaction - Swagger/OpenAPI Integration: Automatically generate tools from API specifications
- Built-in Documentation: Self-documenting API reference
- Secure: Runs in isolated environment with controlled access
- Fast: Built with TypeScript and optimized for performance
Usage
HAL is designed to work with MCP-compatible clients. Here are some examples:
Basic Usage (Claude Desktop)
Add HAL to your Claude Desktop configuration (npx will automatically install and run HAL):
{
"mcpServers": {
"hal": {
"command": "npx",
"args": ["hal-mcp"]
}
}
}With Swagger/OpenAPI Integration and Secrets
To enable automatic tool generation from an OpenAPI specification and use secrets:
{
"mcpServers": {
"hal": {
"command": "npx",
"args": ["hal-mcp"],
"env": {
"HAL_SWAGGER_FILE": "/path/to/your/openapi.json",
"HAL_API_BASE_URL": "https://api.example.com",
"HAL_SECRET_API_KEY": "your-secret-api-key",
"HAL_SECRET_USERNAME": "your-username",
"HAL_SECRET_PASSWORD": "your-password"
}
}
}
}URL-
549ee2d232f4OBSERVED · 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 hal-mcp -- npx -y [email protected]
{
"mcpServers": {
"hal-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (13)
9 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
docs_components | read | |
docs_endpoints | read | |
docs_example | read | |
docs_schemas | read | |
docs_search | read | |
http-delete | destructive | |
http-get | read | |
http-head | read | |
http-options | read | |
http-patch | write | |
http-post | write | |
http-put | write | |
list-secrets | read |
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 | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
http-delete
@astrojs/check, @astrojs/tailwind, astro, basecoat-css, lucide-astro, tailwindcss, typescript, @types/node
@modelcontextprotocol/sdk, zod, yaml, @apidevtools/swagger-parser, @types/node, @types/swagger-parser, typescript, tsx
Gates applied: no_behavioural_pass.
549ee2d232f4full audit observations/trust-audit/mcp-server/deanward__hal.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 | 549ee2d232f4 | SAFE | B | 89 | first audit |
Questions
What is the HAL MCP server?
HAL (HTTP API Layer) is a Model Context Protocol (MCP) server that provides HTTP API capabilities to Large Language Models.
What tools does HAL expose?
13 in total: 9 read-only, 3 that write, and 1 that can delete or overwrite (http-delete). Every one is listed on this page with its risk.
Is HAL 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. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does HAL need?
No credential environment variables were found in its source, so it appears to need none.
How does HAL run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as hal-mcp at 1.0.14.
How current is this page?
The grade is for one exact copy of the source (549ee2d232f4), read on 2026-10-08. The repository is watched and re-audited when it changes.