Skip to content
Back to search

spectral

Browse any app normally. Spectral captures the traffic, understands what each API call does, and generates MCP tools that AI agents can call directly.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/spectral-mcp--spectral/badge.svg)](/listings/spectral-mcp--spectral)

HTML

<a href="/listings/spectral-mcp--spectral"><img src="/api/listings/spectral-mcp--spectral/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

The install script sets up Spectral, installs shell completions, and ensures your PATH is configured:

curl -LsSf https://getspectral.sh/install.sh | bash

If you prefer managing packages yourself, you can install directly with pip or [uv](https://docs.astral.sh/uv/) — but you will need to set up shell completions manually:

pip install spectral-mcp
# or
uv tool install spectral-mcp

See the [documentation](https://www.getspectral.sh/documentation) for setup guides, capture instructions, and CLI reference.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 75 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/spectral-mcp/spectral/main/assets/banner-wide-dark.png">
  4. <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/spectral-mcp/spectral/main/assets/banner-wide-light.png">
  5. <img src="https://raw.githubusercontent.com/spectral-mcp/spectral/main/assets/banner-wide-dark.png" alt="Spectral" width="600">
  6. </picture>
  7. </p>
  8. <p align="center">
  9. <a href="https://pypi.org/project/spectral-mcp/"><img src="https://img.shields.io/pypi/v/spectral-mcp" alt="PyPI"></a>
  10. <a href="https://pypi.org/project/spectral-mcp/"><img src="https://img.shields.io/pypi/pyversions/spectral-mcp" alt="Python"></a>
  11. <a href="https://github.com/spectral-mcp/spectral/actions/workflows/release.yml"><img src="https://github.com/spectral-mcp/spectral/actions/workflows/release.yml/badge.svg" alt="CI"></a>
  12. <a href="LICENSE"><img src="https://img.shields.io/github/license/spectral-mcp/spectral" alt="License"></a>
  13. </p>
  14. <p align="center">
  15. <a href="#install">Install</a> ·
  16. <a href="#why-spectral">Why Spectral</a> ·
  17. <a href="#how-it-works">How it works</a> ·
  18. <a href="https://www.getspectral.sh/documentation"><strong>Documentation</strong></a> ·
  19. <a href="https://www.getspectral.sh/"><strong>Website</strong></a>
  20. </p>
  21. AI agents shouldn't need browser automation. Mobile and web apps talk to private APIs all day — Spectral gives that same access to your AI agents.
  22. <p align="center">
  23. <img src="https://raw.githubusercontent.com/spectral-mcp/spectral/main/assets/demo.gif" width="750" alt="Spectral demo — analyze traffic, then Claude uses the API">
  24. </p>
  25. ## Why Spectral
  26. Most apps — web, mobile, desktop — sit on top of undocumented HTTP APIs. Spectral records the traffic while you browse, uses an LLM to understand what each call does, and generates MCP tools that any AI agent can call.
  27. Spectral supports multiple LLM providers — Anthropic, OpenRouter, OpenAI, Ollama, and any OpenAI-compatible endpoint. Run `spectral config` to pick your provider and model. Spectral will prompt for it on first analysis.
  28. - **Works everywhere.** Websites, mobile apps (Android), desktop apps, CLI tools — if it speaks HTTPS, Spectral can capture it.
  29. - **Understands what you do, not just what the network sends.** Spectral correlates your clicks and navigation with API calls to figure out the business meaning of each endpoint — not just its shape.
  30. - **Tools that fix themselves.** When a generated tool fails at runtime, the MCP server feeds the error back to an LLM and patches the tool automatically.
  31. - **LLM at build time, not at runtime.** The LLM is only used during analysis and self-repair. Once your tools work, every call is a direct HTTP request — fast, cheap, and deterministic.
  32. - **Faster than browser automation.** No headless browser, no fragile selectors, no waiting for pages to render. Spectral tools call the API directly, which is orders of magnitude faster and more reliable than controlling a browser with an agent.
  33. - **Also generates API specs.** Beyond MCP tools, Spectral can produce OpenAPI 3.1 specs from REST traffic and GraphQL SDL schemas from GraphQL traces — useful for documentation, code generation, or feeding other tools.
  34. ## Install
  35. The install script sets up Spectral, installs shell completions, and ensures your PATH is configured:
  36. ```bash
  37. curl -LsSf https://getspectral.sh/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 53 on GitHub
  38. ```
  39. If you prefer managing packages yourself, you can install directly with pip or [uv](https://docs.astral.sh/uv/) — but you will need to set up shell completions manually:
  40. ```bash
  41. pip install spectral-mcp
  42. # or
  43. uv tool install spectral-mcp
  44. ```
  45. See the [documentation](https://www.getspectral.sh/documentation) for setup guides, capture instructions, and CLI reference.
  46. ## How it works
  47. 1. **Capture** — Chrome extension (web) or MITM proxy records traffic while you use the app
  48. 2. **Analyze** — An LLM correlates your actions with API calls, infers endpoint patterns, and business meaning
  49. 3. **Authenticate** — The CLI detects the auth flow and generates a login script. Run it once; the MCP server refreshes automatically
  50. 4. **Use** — Start the MCP server. AI agents call the API directly
  51. ## License
  52. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.