Does phloem require internet or external services?

No. Phloem is fully offline and zero-config—all data stays local on your machine. There are no external dependencies or cloud requirements.

What is a causal graph and how does phloem use it?

A causal graph is a data structure that represents relationships and dependencies between concepts. Phloem uses causal graphs to store and query structured AI memory, allowing you to model how ideas and facts connect.

How do I install and set up phloem?

Download the binary for your platform from the releases page (e.g., phloem-darwin-arm64.mcpb for macOS ARM64) and run it as an MCP server over stdio. No additional configuration needed.

Can I export or migrate my phloem data?

The registry metadata does not specify export or migration capabilities. Check the GitHub repository for details on data portability and backup options.

What are alternatives to phloem for local AI memory?

Other local-first options include vector databases like Chroma or Milvus, or graph databases like Neo4j. Phloem's differentiator is its focus on causal relationships and zero-config offline operation.

MCP ServerSTDIOOfficialv0.1.8

Canopyhq Phloem MCP Server

Build local-first AI memory systems using causal graphs that run entirely offline with zero configuration. For developers who need persistent, structured context that stays on their machine.

io.github.CanopyHQ/phloem

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Canopyhq Phloem MCP server does

How models use it and what it is built for.

Build local-first AI memory systems using causal graphs that run entirely offline with zero configuration. For developers who need persistent, structured context that stays on their machine.

Connect to Canopyhq Phloem

Local install — runs as a subprocess.

https://github.com/CanopyHQ/phloem/releases/download/v0.1.8/phloem-darwin-arm64.mcpb

Resources

Where to find authoritative docs and source for Canopyhq Phloem.

Source repository

Example prompts for Canopyhq Phloem

Paste any of these into Agent Studio after connecting Canopyhq Phloem.

Create a causal graph node for this conversation and link it to previous sessions
Query my local memory for all facts related to project architecture decisions
Show me the causal relationships between these three concepts in my knowledge base
What does the phloem schema support for storing structured relationships?

Canopyhq Phloem MCP server — FAQ

Common questions about connecting and running Canopyhq Phloem.

Does phloem require internet or external services?
No. Phloem is fully offline and zero-config—all data stays local on your machine. There are no external dependencies or cloud requirements.
What is a causal graph and how does phloem use it?
A causal graph is a data structure that represents relationships and dependencies between concepts. Phloem uses causal graphs to store and query structured AI memory, allowing you to model how ideas and facts connect.
How do I install and set up phloem?
Download the binary for your platform from the releases page (e.g., phloem-darwin-arm64.mcpb for macOS ARM64) and run it as an MCP server over stdio. No additional configuration needed.
Can I export or migrate my phloem data?
The registry metadata does not specify export or migration capabilities. Check the GitHub repository for details on data portability and backup options.
What are alternatives to phloem for local AI memory?
Other local-first options include vector databases like Chroma or Milvus, or graph databases like Neo4j. Phloem's differentiator is its focus on causal relationships and zero-config offline operation.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio