M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
D

Domain Memory Agent

Community
An MCP server for domain-specific knowledge management with semantic search and summarization.
How to install ↓ Compare GitHub source repository ↗
Category
Other #221 of 230
Stars
★ 2.8k Very popular
Transport
stdio (local process)
Runtime
Node.js
Credentials
No credential needed
License
MIT
Last commit
28FMRS · D

Evidence is limited to the server manifest and a one-line marketplace description. This profile confirms the name, version, npm package identifier, stdio transport, repository-level MIT license, and the TF-IDF/extractive-summarization positioning. Tool names, client compatibility, permissions, and security details are not documented in the sources, so those fields are left empty rather than guessed.

Strongest · Maintenance 12/20 Weakest · Documentation 3/20

Reliability
4/20
Security and permissions
5/20
Maintenance
12/20
Documentation
3/20
Setup experience
4/20
Why each score
Reliability 4/20
Only the server.json manifest and a one-line description are available; there is no source code, tests, or CI evidence for this server, so the MCP init handshake, tool list, and error handling cannot be verified. The description calls TF-IDF 'semantic search', which is a minor overstatement. Following the missing-evidence deduction rule, reliability is conservatively scored 4.
Security and permissions 5/20
No red-line issues (malware, credential theft, destructive defaults, real tokens in install examples) are visible in the manifest, but without source code we cannot verify least privilege, data boundaries, external network use, or confirmation flows for dangerous operations. The score therefore stays mid-low at 5.
Maintenance 12/20
The repository as a whole appears actively maintained: MIT license, not archived, recent release v4.33.0, validator scripts, and issue tracking. However, there is no granular evidence for this specific server package's own release history, commit activity, dependency updates, or security-response channel, so full marks are not justified; scored 12.
Documentation 3/20
The repository README covers the entire marketplace and gives this server only a single-line description ('knowledge base with TF-IDF semantic search and extractive summarization'). There are no install/auth instructions, tool parameter references, limits, cost notes, troubleshooting guides, or examples specific to domain-memory-agent. Documentation is near the lowest anchor, scored 3.
Setup experience 4/20
The manifest specifies the npm package identifier, version, and stdio transport, which gives a starting point, but there are no step-by-step installation instructions, client configuration examples, prerequisites, or compatibility notes for this server, and we cannot confirm the package is actually published and runnable. Setup is scored 4.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

Best for

  • MCP users who want a lightweight, dependency-light knowledge base.
  • Cases where TF-IDF retrieval and extractive summarization are sufficient.
  • Developers exploring non-official domain knowledge servers inside the Claude Code plugin marketplace ecosystem.

Not for

  • High-fidelity semantic search requiring vector/embedding retrieval or neural summarization.
  • Production knowledge platforms that need documented authentication, encryption, and access controls.
  • Users who need a complete tool catalog or official support commitments before installing.

Required permissions

  • The source does not document an explicit permission list.
  • Because transport is stdio, the server is launched as a local process by the MCP client; actual filesystem or network access depends on the npm package implementation, which is not described in the supplied manifest.

Risks and side effects

  • Unofficial third-party server; it is not maintained by Anthropic, Claude Code, or the upstream product/protocol owner.
  • Installing an npm package carries normal supply-chain integrity and dependency risks.
  • The manifest does not list concrete tool names, security model, or data-handling guarantees.
  • Storage, encryption, and retention of knowledge-base data are not described in the provided materials.

Setup

Before you start

Runtime：Node.js

The manifest declares the npm package @claude-code-plugins-plus/[email protected] with stdio transport, but it does not provide a server-specific install snippet. Repository-level README instructions show the general marketplace route: pnpm add -g @intentsolutionsio/ccpi followed by ccpi install <plugin>; alternatively, Claude Code's built-in command /plugin marketplace add jeremylongshore/claude-code-plugins. No standalone MCP client configuration JSON example is given in the supplied sources.

Check that it works

After installing, restart Claude Code and check that the domain-memory-agent tools appear in the client's tool list; then issue a search request — a returned semantic search result confirms the connection works.

Troubleshooting

  1. Before configuring, verify that package @claude-code-plugins-plus/[email protected] exists on npm with that version.
  2. Ensure the MCP client can spawn stdio processes and that the runtime required by the npm package is available.
  3. If the server does not appear, inspect MCP client logs for startup or transport errors.
  4. If using the repository manifest, check that the path plugins/mcp/domain-memory-agent/server.json matches the client configuration.
  5. If no tools show up, inspect the installed package's own documentation or source; the supplied materials do not list tool names.

Things to try

Once connected, you can ask your AI assistant things like:

  • Search the domain memory knowledge base for entries about semantic retrieval
  • Summarize the notes stored in the knowledge base about this project
  • Add this domain knowledge document to the domain-memory-agent knowledge base
  • List all domain documents currently stored in the knowledge base

Use cases

Maintaining a searchable knowledge base for a specific technical or business domain.
Retrieving relevant knowledge snippets using TF-IDF-based semantic search.
Producing extractive summaries from stored domain knowledge.
Adding knowledge-management capabilities without additional ML model dependencies.

Overview

The Domain Memory Agent is an MCP server whose manifest describes domain-specific knowledge management with semantic search and summarization. It is listed in the jeremylongshore/claude-code-plugins-plus-skills repository under plugins/mcp/domain-memory-agent. The marketplace entry describes it as a knowledge base with TF-IDF semantic search and extractive summarization that requires no ML dependencies. The declared npm package is @claude-code-plugins-plus/domain-memory-agent version 1.0.0, using stdio transport. The repository is MIT-licensed, and this server is not maintained by the upstream product/protocol owner.

Similar servers

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →
Compare with other MCP servers

More servers from this repository

AI Experiment Logger MCP ServerAI Experiment LoggerConversational API DebuggerDesign To CodeLumera Agent MemoryProject Health AuditorWorkflow Orchestrator

Source revision ebea1067983c Data synced 2026-10-12 Read the FMRS scoring method