Phaedo carries a local preference projection into assistants and offers consultation tools at selected decision points.
Phaedo carries a local preference projection into assistants and offers consultation tools at selected decision points.
Phaedo exposes a projection of the user's cognitive fingerprint to a compatible assistant. The documented tools request that projection, consult a decision pattern and check authorization context. This is a personalization interface, rather than a general-purpose approval system. Inspect the actual projection and policy before allowing its results to influence an automated workflow.
The npm package phaedo-mcp runs over stdio. A local JSON fingerprint can be supplied with PHAEDO_FINGERPRINT; the project also documents pairing with its phone application. Consultation can use a configured model endpoint, with additional model, URL and API-key settings. The standard local mode is implemented, while the enhanced privacy transport is described as future work.
Use a non-sensitive sample fingerprint, request its injection and ask a consultation question with a known context. Compare the answer with the supplied preferences and inspect any local consultation receipt. Pairing and projection access follow the application's authorization flow. Preferences should inform a decision, while permission to take an external action should remain explicit in the workflow using the tool.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| phaedo_request_injection | Request the configured fingerprint projection. |
| phaedo_consult | Consult the configured decision pattern. |
| phaedo_check_authorization | Inspect the configured authorization context. |
{
"mcpServers": {
"phaedo": {
"command": "npx",
"args": [
"-y",
"phaedo-mcp"
],
"env": {
"PHAEDO_FINGERPRINT": "/ABSOLUTE_PATH/fingerprint.json"
}
}
}
}Node.js, a configured fingerprint projection and the documented consultation endpoint settings when consultation is enabled.
| Variable | Description | Required |
|---|---|---|
| PHAEDO_FINGERPRINT | Absolute path to a local fingerprint JSON file. | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Enables AI assistants to securely interact with Azure DevOps through a standardized protocol.