OutsourceSAFE
Give your AI assistant its own AI assistants.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP (Model Context Protocol) server that enables AI applications to outsource tasks to various model providers through a unified interface.
Compatible with any AI tool that supports the Model Context Protocol, including Claude Desktop, Cline, and other MCP-enabled applications. Built with FastMCP for the MCP server implementation and Agno for AI agent capabilities.
Features
- 🤖 Multi-Provider Support: Access 20+ AI providers through a single interface
- 📝 Text Generation: Generate text using models from OpenAI, Anthropic, Google, and more
- 🎨 Image Generation: Create images using DALL-E 3 and DALL-E 2
- 🔧 Simple API: Consistent interface with just three parameters: provider, model, and prompt
- 🔑 Flexible Authentication: Only configure API keys for the providers you use
Configuration
Add the following configuration to your MCP client. Consult your MCP client's documentation for specific configuration details.
{
"mcpServers": {
"outsource-mcp": {
"command": "uvx",
"args": ["--from", "git+https://github.com/gwbischof/outsource-mcp.git", "outsource-mcp"],
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"GOOGLE_API_KEY": "your-google-key",
"GROQ_API_KEY": "your-groq-key",
"DEEPSEEK_API_KEY": "your-deepseek-key",
"XAI_API_KEY": "your-xai-key",
"PERPLEXITY_API_KEY": "your-perplexity-key",
"COHERE_API_KEY": "your-cohere-key",
"FIREWORKS_API_KEY": "your-fireworks-key",
"HUGGINGFACE_API_KEY": "your-huggingface-key",
"MISTRAL_API_KEY": "your-mistral-key",
bc64a7e80174OBSERVED · 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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add outsource-mcp --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx outsource-mcp{
"mcpServers": {
"outsource-mcp": {
"command": "uvx",
"args": [
"outsource-mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
outsource_image | read | |
outsource_text | 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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
bc64a7e80174full audit observations/trust-audit/mcp-server/gwbischof__outsource.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 | bc64a7e80174 | SAFE | B | 89 | first audit |
Questions
What is the Outsource MCP server?
Give your AI assistant its own AI assistants.
What tools does Outsource expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Outsource 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 Outsource need?
It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Outsource run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as outsource-mcp.
How current is this page?
The grade is for one exact copy of the source (bc64a7e80174), read on 2026-10-08. The repository is watched and re-audited when it changes.