mcpField
M

memorymesh

Local
@sparkvibe-ioMemory & Knowledge

About memorymesh

Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "sparkvibe-io-memorymesh": {
      "command": "uvx",
      "args": [
        "memorymesh"
      ]
    }
  }
}
Run commanduvx memorymesh

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimemorymesh4.1.0

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
pinbooleanNoPin this memory. Pinned memories have maximum importance (1.0), never decay, and are always prominent in recall. Default: false.
textstringYesThe text content to remember.
scopeenumNoWhere to store the memory. 'project' (default) stores in the current project's database. 'global' stores in the user-wide database for preferences and facts that apply across all projects.project | global
categoryenumNoMemory category. When set, scope is automatically routed (e.g. 'preference' -> global, 'decision' -> project).preference | guardrail | mistake | personality | question | decision | pattern | context | session_summary
metadataobjectNoOptional key-value metadata to attach to the memory (e.g., {"source": "user", "topic": "preferences"}).
importancenumberNoImportance score between 0.0 and 1.0. Higher values make the memory more prominent during recall. Default: 0.5.
on_conflictenumNoHow to handle contradictions with existing memories. 'keep_both' (default) stores both and flags the contradiction. 'update' replaces the most similar existing memory. 'skip' discards the new memory if a contradiction is found.keep_both | update | skip
redact_secretsbooleanNoIf true, automatically redact detected secrets (API keys, tokens, passwords) before storing. Default: false.
auto_categorizebooleanNoIf true, automatically detect category from the text. Also enables auto-importance scoring. Default: false.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.