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 Memphora MCP server?
Add persistent memory to AI assistants. Store and recall info across conversations.
How to install Memphora
Copy-paste configuration for popular MCP clients.
MEMPHORA_API_KEYrequiredsecretYour Memphora API key from memphora.ai/dashboard
MEMPHORA_USER_IDUnique identifier for your memories
{
"mcpServers": {
"memphora": {
"command": "uvx",
"args": [
"memphora-mcp",
"-m",
"memphora_mcp.server"
],
"env": {
"MEMPHORA_API_KEY": "<YOUR_MEMPHORA_API_KEY>",
"MEMPHORA_USER_ID": "<YOUR_MEMPHORA_USER_ID>"
}
}
}
}Related MCP servers

PraisonAI
Build autonomous, self-reflecting AI agents and connect them to any MCP server in minutes.

Transform ComfyUI workflows into AI-callable tools via MCP protocol.
Rule-tiered AST and sqlite-vec capability oracle for A-MEM agent workflows.

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

io.github.MendleM/pipepost
MCP server to publish to Substack, Ghost, Dev.to, WordPress, LinkedIn + 5 more from Claude Code.

MemoryGuard
Local-first governed MCP memory backend for coding agents.