Skip to content
Agentmart
Submit a tool

Provena Agent Memory

Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.

Connector by admiralpunk · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 7
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/admiralpunk-provena-memory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
4 read · 2 write · 0 delete · 1 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Python package

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • memory_capture_turn
  • memory_context
  • memory_explain
  • memory_search

Write 2 · Create, change, send or run things.

  • memory_propose_claim
  • memory_record_event

Not yet classified 1 · We could not tell from the name and description.

  • memory_remember

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • PROVENA_API_KEY

Other settings (environment variables or headers).

  • PROVENA_API_URL
  • PROVENA_SCOPE_ID

Network hosts it talks to 2

  • github.com · found in code
  • raw.githubusercontent.com · found in code

Files it touches

  • Your home directory (~)
  • ~/.codex/config.toml

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • memory_capture_turn

    Capture and extract facts from one host conversation turn; output remains low-authority candidate memory.

  • memory_context

    Get attributed, exact-scope memory context relevant to the current request, including candidate status and source authority.

  • memory_explain

    Show the claim, original evidence, authority, review actions, conflicts, and retrieval history.

  • memory_propose_claim

    Create a candidate claim backed by an event in the configured scope. Human review is required to activate it.

  • memory_record_event

    Preserve agent-supplied source text as a low-authority event; this does not create a durable active claim.

  • memory_remember

    Atomically save an agent-supplied event and candidate claim; return IDs, authority, and status.

  • memory_search

    Retrieve semantically relevant reviewed or provisional claims with status, IDs, and source authority.

Signals

Stars
7
Forks
6
Open issues
9
Weekly downloads
175
Last commit
Oct 15, 2026 (13 days ago)
Last release
Sep 29, 2026 (29 days ago)
Last package publish
Sep 29, 2026 (29 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.admiralpunk/provena-memory
Version
0.1.15
Auth
API key
Packages
pypi provena-agent-memory
License
MIT
Repository
github.com/admiralpunk/Provena
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Provena Agent Memory MCP server. Agent Mart. https://agentmart.dev/connectors/admiralpunk-provena-memory (last updated 2026-10-25)