Stompy – AI Memory for Claude & MCP Agents

ai.stompyPublished by stompy.aiOfficial publisherv1.0.0Updated Oct 24, 2026

Persistent AI memory with semantic search, conflict detection, and ticketing.

VerifiedStreamable HTTPWeb executableDatabasesProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Stompy gives an assistant persistent project memory with semantic search, conflict detection, document ingestion and ticket management.

What you can do
Stompy is a hosted memory service for AI agents. Assistants can lock content as immutable versioned snapshots, recall it by topic, and run hybrid keyword plus vector search across stored project knowledge. It also detects contradictions between stored knowledge, ingests documents with AI chunking, manages tickets with per-type state machines and a status board, creates isolated projects with cross-project search, and runs read-only SQL queries against a project database.
When to use it
Useful when you want context to survive between chat sessions, such as keeping project decisions, notes and reference documents available to an assistant. Also suited to teams that want contradiction checks over accumulated knowledge or lightweight ticket tracking alongside their memory store.
Requirements
A remote MCP endpoint reached over streamable HTTP; no local package or runtime is needed. OAuth2 authentication is required, and the MCP client prompts for browser authorization on first connection. Network access to the hosted endpoint is needed.
Before you install
Stored content, ingested documents and project knowledge are sent to a third-party hosted service, so avoid confidential material unless that is acceptable. The server can write and change data through context locking, document ingestion, project creation and ticket create/update/delete operations. Authorization is granted through an OAuth2 browser flow, so review the scopes requested.

Installation

In SourceWeft

  1. Open Stompy – AI Memory for Claude & MCP Agents in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.stompy%2Fstompy/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "stompy-ai-memory-for-claude-agents": {
      "type": "http",
      "url": "https://mcp.stompy.ai/"
    }
  }
}

README

Stompy – AI Memory for Claude & MCP Agents

Persistent memory system that prevents context loss between AI sessions. Store, search, and recall project knowledge across conversations.

Features

  • Semantic Search — Hybrid keyword + vector search over your project contexts
  • Conflict Detection — NLI-powered contradiction detection across stored knowledge
  • Ticket Management — Built-in ticketing with state machines per ticket type
  • Document Ingestion — Upload and process documents with AI chunking
  • Multi-Project — Isolated storage per project with cross-project search

Quick Start

VS Code / Cursor / Windsurf

Search @mcp stompy in the extensions gallery, or add manually:

json
// .vscode/mcp.json{  "servers": {    "stompy": {      "type": "http",      "url": "https://mcp.stompy.ai"    }  }}

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "stompy": {      "url": "https://mcp.stompy.ai"    }  }}

Claude Code

bash
claude mcp add stompy --transport streamable-http https://mcp.stompy.ai

Tools

ToolDescription
lock_contextStore content as immutable versioned snapshot
recall_contextRetrieve locked context by topic
context_searchHybrid semantic + keyword search
ticketCRUD + lifecycle for project tickets
ticket_boardView ticket board grouped by status
detect_conflictsDetect contradictions using NLI
ingest_documentIngest documents with AI processing
project_createCreate a new project with isolated storage
db_queryRead-only SQL queries against project database

Authentication

Stompy uses OAuth2 authentication. On first connection, your MCP client will prompt you to authorize via browser.

Links

  • Website: stompy.ai
  • MCP Endpoint: https://mcp.stompy.ai

Source: README.md at commit 0aabbe8

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.