Skip to main content
Glama

Stellara

PR CI License: MIT

Stellara is a self-hosted AI tool gateway for Firecrawl, Exa, Qdrant, and an embeddings backend. It exposes one token-protected HTTP and Model Context Protocol (MCP) interface for LLM clients such as Claude Desktop and ChatGPT connectors.

The gateway centralizes upstream credentials, authentication, rate limits, response validation, and network safeguards. It also provides Playwright browser sessions, per-user vector memory, and domain availability checks.

Capabilities

  • web_* — search, scrape, crawl, extract, and make guarded HTTP or GraphQL requests.

  • browser_* — run interactive Playwright sessions for navigation, forms, screenshots, PDFs, and JavaScript evaluation.

  • memory_* — store and retrieve per-user context through embeddings and Qdrant.

  • domain_availability — check domain registration through RDAP with a WHOIS fallback.

  • OAuth 2.1 and MCP — connect token-based clients or OAuth-capable MCP clients through one gateway.

See the tool reference for the complete catalog.

Related MCP server: webcrawl-mcp

Requirements

  • Node.js 24 or newer

  • pnpm 10.33.4 through Corepack

  • Provider credentials for the features you enable

  • Docker for the container deployment

Local development

corepack enable
pnpm install
cp .env.example .env

Set a public base URL, at least one STELLARA_TOKEN_<USERID>, and the required Firecrawl values in .env. Optional Exa, Qdrant, and embeddings credentials enable their matching tool families.

Start the development server:

pnpm dev

The health endpoint is available at http://localhost:8787/health unless PORT is changed.

Container deployment

The supported container image is ghcr.io/sebastian-software/stellara. Versioned releases publish a stable patch tag plus the moving minor and latest tags.

Copy .env.example to .env, configure the external proxy network, prepare stellara-data/ for UID/GID 999, and then start the service:

docker compose up -d

Read the operations guide before exposing the service. It covers proxy trust, OAuth persistence, backup, and recovery.

Development and tests

The required local quality gate is:

pnpm agent:check

This command runs type checking, linting, formatting verification, and the hermetic unit suite. Live provider tests are optional, local-only, and require credentials supplied through normal environment variables:

pnpm test:integration

GitHub Actions never receives or runs these integration credentials.

Documentation

Some in-depth documentation is currently available in German. Translation work is tracked in the public issue tracker.

Contributing and support

Read CONTRIBUTING.md before opening a pull request. Use GitHub Issues for reproducible bugs and focused feature proposals. See SUPPORT.md for the project support policy.

Report security vulnerabilities privately as described in SECURITY.md. Do not disclose vulnerabilities in public issues.

License

Stellara is available under the MIT License.

A
license - permissive license
Not graded
quality - not tested
A
maintenance

Maintenance

UpdatingMaintainers
UpdatingResponse time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • OCR, transcription, file extraction, and image generation for AI agents via MCP.

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

  • Connect MCP clients to 2,000+ AI models without managing provider API keys.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sebastian-software/stellara'

If you have feedback or need assistance with the MCP directory API, please join our Discord server