What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the RuleDrift MCP server?
Test whether AI agents retain critical instructions as conversations grow.
How to install RuleDrift
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"rule-drift": {
"command": "npx",
"args": [
"-y",
"rule-drift",
"mcp"
]
}
}
}Related MCP servers

Volante
Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.

Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.

Prolog Reasoner
SWI-Prolog logic solver for LLMs—bridge natural language reasoning with formal symbolic computation.

RillCoin
AI agent wallets, Proof of Conduct reputation, and concentration decay on L1

Local document search over your folders: hybrid keyword+semantic, fully offline, read-only

io.github.ricardo-hdrn/mcp-await
Condition watcher for AI assistants — wait for ports, files, URLs, processes, and more