Persome MCP server

Read from the package source without running it. The installed server may list more.

• attention_trajectory

  Where the user's attention went, with DWELL (time actually spent).

• behavior_patterns

  **CALL FIRST for "who is this user / how do they work" context** — the learned behavior model, not raw memories.

• correct_memorywrite action

  Update the user's memory when they tell you something in it is WRONG.

• current_context

  **ALWAYS CALL** for present-tense or ambiguous-pronoun questions about the user's state.

• entity_graph

  **CALL for "who is X / how does X relate to people & projects"** — the relation graph around one identity, optionally AS OF a past date.

• get_model_snapshot

  Return the versioned Point/Line/Face/Volume/Root personal-model snapshot.

• get_schema

  Return the memory organization spec (file naming, what each prefix means).

• list_memories

  **ALWAYS CALL FIRST** on the first personal-context turn of a conversation.

• read_memory

  Read the full contents of ONE memory file the user has on disk.

• read_receipt

  Dereference ONE memory receipt — the `⟨entry_id:path⟩` handles that `search`'s `chains` narrative and other tools hand out.

• read_recent_capture

  Hydrate ONE raw screen capture — the actual visible_text, focused input value, URL, and (optionally) screenshot from the buffer.

• recent_activity

  **ALWAYS CALL** when the user references yesterday, last week, earlier, or recently.

• rememberwrite action

  Write a durable finding back into Persome memory so later agents can reuse it. Call this when you learn something durable about the user, their project, a tool, or a decision while running.

• search
• search_captures

  **ALWAYS CALL** (usually in parallel with `search`) when the user mentions a keyword they'd have typed or read on screen.

• verify_fact

  **CALL BEFORE STATING time-sensitive facts as current** — freshness check for a single claim against the user's memory.

• Code scan156 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 22 days ago15/15
• Maintainer identityregistry namespace matches repository owner7/10

Safety score

91/100

higher than 88% of 4,456 AI and agents servers

Tools

16

the typical AI and agents server has 7

Tools that change things

13%

typical: 3%. Fewer write tools means less an agent can break

GitHub stars

1,337

more than 95% of 2,733 AI and agents servers

Downloads a week

29

more than 10% of 1,712 AI and agents servers with a package

Persome: common questions

Is Persome MCP server safe?

Yes, by our scan: it is graded A (91/100). Read the Persome safety report

How do I install Persome?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Persome need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Persome maintained?

The last commit was 30 days ago (2026-10-16). The latest release is v0.3.2.

What can I use instead of Persome?

Servers from other publishers that do the same job: Basic Memory MCP server, Agent Recall MCP server and HOL Guard MCP server.

How does Persome compare with other AI and agents MCP servers?

safety score 91/100 (higher than 88% of 4,456 AI and agents servers); tools 16 (the typical AI and agents server has 7); tools that change things 13% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.