Advertise
MCP.so
Sign In

Palinode MCP Server

@phasespace-labs

RepositoryHomepage

Basic information

Category

Other

License

MIT

Author

phasespace-labs

About Palinode MCP Server

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

Palinode MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "palinode": {
      "type": "http",
      "url": "http://your-server:6341/mcp/"
    }
  }
}

Palinode MCP Server tools

33

Session-start context digest for the resolved project scope

Hybrid BM25 + vector search with category filter; `resolve` attaches bounded evidence and a resolution per hit

What memory holds *right now* for a question or one record — what stands, what replaced what, conflicts with both sides intact, and what is explicitly unknown

Store a typed memory (person, decision, insight, project)

Browse memory files by type, filter by core status

Read the full content of a memory file

Fetch a URL and save as research

Health check — file counts, index stats, service status

Entity graph — cross-references between memories

Preview or run LLM-powered compaction

Retire one memory that's wrong or obsolete — archive it, or supersede it with a named replacement

Bring an archived memory back into default recall — the inverse of `archive`

Withdraw one preference's mention-level retraction from one memory

Take a forget request back — restore what it archived, un-strike what it retracted

Archive ephemeral memories whose TTL has expired

What changed in the last N days

Trace a fact back to the commit that recorded it

Compose a fact's full provenance lineage — sources, saved/changed commits, supersession, typed links, recall

Git history for a file with diff stats and rename tracking

Revert a file to a previous commit (safe, creates new commit)

Sync memory to a remote git repo

Prospective recall — auto-inject when a topic comes up

Health scan — orphans, stale files, missing fields

Advisory project-memory review that proposes corrective operations without writing them

Capture summary, decisions, and blockers at end of session

List, show, or activate versioned LLM prompts

Before saving, surface existing files that overlap the draft

Find semantic matches for broken `[[wikilinks]]`

Fast diagnostic pass — 18+ checks across paths, services, config, index

Full diagnostic with canary write test (~10–15s)

Find top-K semantically related files NOT already wiki-linked — surface implicit relationships for cross-link proposals

Given a short topic phrase, return whether any existing wiki page already covers it (binary `covered` / `best_match` / `similarity`)

Dependency tree (or unblocked-items list) from `depends_on` / `blocks` / `parallel_with` frontmatter on ProjectSnapshots

Overview

What is Palinode?

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

How to use Palinode?

The README includes setup instructions such as ``python -m bench.abstention. It measures false positives for no-answer queries.

Key features of Palinode

  • Python 3.11+
  • Ollama with bge-m3 (ollama pull bge-m3, ≈1.2 GB), or another supported
  • model: "qwen2.5:14b-instruct"
  • Operation-based compaction — Structured operations are schema-checked and applied as reviewable git commits
  • Multi-transport MCP — stdio for local, Streamable HTTP for remote. One server, any IDE on any machine

Use cases of Palinode

  • Connect an MCP-compatible client to this repository's service.
  • Review the README-backed setup before enabling it in production.

Frequently asked questions

1

Where is the source code for Palinode?

The source code is linked from the repository URL on this page.

2

Does Palinode include a standard MCP config?

If the README contains a parseable MCP configuration block, it is shown in the Config tab.

Comments

More Other MCP servers

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

LoadOptimizer

LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K
Advertise