Qdrant Memory MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Qdrant Memory MCP
One Memory. Multiple Agents. No Lock-in.
The Codex plugin candidate adds guided local setup, read-only native-memory import and verified JSON/Markdown handoff. It is versioned independently and does not add a second Runtime. See the executed validation and limits. Exports remain readable without this plugin or a subscription; native adoption is verified separately from file creation.
Durable, portable, and permission-aware memory for AI agents — distributed as an MCP adapter over the Qdrant Memory Runtime.
For shared production deployments, read the deployment security guide. Owner-only database write credentials are required independently of MCP grants. Configure destination protection and shared doctor before deployment. See the Owner support record for support limits.
One Memory, Multiple Agents — opt-in shared owner
The distribution adds an opt-in single-owner service and stdio bridge. Install Runtime 0.7.1 to use them. See shared integration guide. Private defaults are unchanged. Native Provider automatic shared extraction is deferred.
A WorkBuddy connector and a DeepSeek Harness bundle reuse this stdio MCP, the managed launcher and the canonical Skill.
Persistent, scoped memory for AI agents through four explicit stdio MCP tools.
This repository distributes the existing Python Runtime.
Its metadata-only wheel contains no Python business implementation. The console
script points directly to qdrant_memory.standalone:main and depends on
hermes-plugin-qdrant-memory[mcp]==0.7.1.
See 0.3.5 release notes for the Runtime pin and upgrade guidance.
Before using an exact-version installation command, confirm that version on the PyPI release page. The published 0.3.4 guide remains available for the previous release.
Versions: MCP distribution 0.3.5 pins Runtime 0.7.1, which supports MCP
Python SDK 1.x and 2.x (mcp>=1.30,<3). The four scoped tools and stdio
launch arguments are the same for both SDK majors. The commands below use
these exact versions. Release
artifacts are available through the distribution PyPI page
and Runtime PyPI page.
See release checklist for the publishing sequence.
Runtime, optional Agent Skill and MCP distribution versions are independent. The Skill is usage guidance, not a runtime dependency. Hermes retains its native MemoryProvider, automatic extraction and prefetch. Ordinary MCP performs only explicitly requested memory operations. It does not automatically extract every conversation turn.
Related MCP server: CarpeOS MCP Server
Harness support matrix
Verification levels: configuration example only, protocol-level tested, official SDK/CLI tested, real host tested, real desktop GUI tested, not verified.
Host | Native Provider | Explicit MCP tools | Automatic capture | Automatic recall | Shared Owner | Remote access | Verification |
Hermes | Yes | Yes (via standalone) | Yes | Yes | Opt-in | Yes | Real host tested |
OpenCode | No | Yes | No | No | Via Owner | Yes | Real host tested (dual-device) |
Pi | No | Yes (extension) | Opt-in adapter | Opt-in adapter | Via Owner | Yes | Real host tested |
DeepSeek Harness | No (lifecycle adapter) | Yes (DSH bundle) | Opt-in preview | Opt-in preview | Via Owner | Yes | DSH 0.2.2-rc.1 CI host tested; real model/GUI unverified |
WorkBuddy | No | Yes (connector) | No | No | Via Owner | Yes | Real desktop GUI tested |
Codex | No | Yes | No | No | Via Owner | Yes | Official CLI tested |
This distribution does not auto-extract conversations for any MCP host. Automatic capture and recall require a native provider or a lifecycle adapter. The DSH native preview is opt-in and source-merged, but its npm package is private and Runtime 0.7.1 is published. Real DSH AgentLoop, model, and desktop GUI evidence remains pending. See the Codex validation record for the tested CLI, source revisions and model providers; desktop GUI and native-memory adoption are separate verification boundaries.
Install and initialize
For the shortest currently supported local setup, follow the Ollama quickstart (中文). It covers an existing model, installing a missing model, a separate WorkBuddy profile, connection settings and a first save/search check. No Qdrant server, Docker, cloud account or embedding API key is needed for that local path. Python/uv and one-time profile configuration are still required for this direct route. The managed WorkBuddy connector and DSH bundle prepare those dependencies from Node.js instead.
Requires Python 3.11+ and either uv or a Python
virtual environment. You must configure storage and an embedding service.
For the example below, run Ollama and install qwen3-embedding:4b yourself.
Create an operator-owned profile directory and save qdrant-memory.json inside:
{
"schema_version": 1,
"scope": {"user_id": "my-user", "agent_id": "my-agent"},
"qdrant": {"mode": "embedded", "collection": "qdrant_memory"},
"embedding": {
"mode": "plugin", "provider": "ollama", "model": "qwen3-embedding:4b",
"base_url": "http://127.0.0.1:11434", "dimensions": 2560, "distance": "Cosine"
}
}Initialize, then launch (replace /path/to/profile with your absolute path):
uvx --from qdrant-memory-mcp==0.3.5 qdrant-memory-mcp --home /path/to/profile init
uvx --from qdrant-memory-mcp==0.3.5 qdrant-memory-mcp --home /path/to/profile mcpThe command without --home uses ~/.qdrant-memory, independent of Hermes.
Configure and initialize that directory before letting a Registry client launch
uvx --from qdrant-memory-mcp==0.3.5 qdrant-memory-mcp mcp.
The executable name matches the package name.
The Registry's positional mcp selects protocol mode. Its optional named
--home precedes mcp when a client supplies a custom profile.
Alternatively:
python3 -m venv .venv
.venv/bin/python -m pip install qdrant-memory-mcp==0.3.5
.venv/bin/qdrant-memory-mcp --home /path/to/profile init
.venv/bin/qdrant-memory-mcp --home /path/to/profile mcpOn Windows use .venv\Scripts\python.exe and
.venv\Scripts\qdrant-memory-mcp.exe.
Qdrant embedded, self-hosted server and Cloud, plus Ollama and OpenAI-compatible
embeddings, are configured in the Runtime's configuration reference.
Keep credentials in operator environment variables (QDRANT_API_KEY,
EMBEDDING_API_KEY, or configured names). Never commit their values.
Initialization against an existing collection requires explicit operator choice.
Do not use a production destination for a first test.
Connect a client
Codex config.toml example:
[mcp_servers.qdrant_memory]
command = "uvx"
args = ["--from", "qdrant-memory-mcp==0.3.5", "qdrant-memory-mcp", "--home", "/path/to/profile", "mcp"]OpenCode opencode.json example:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"qdrant_memory": {
"type": "local",
"command": ["uvx", "--from", "qdrant-memory-mcp==0.3.5", "qdrant-memory-mcp", "--home", "/path/to/profile", "mcp"],
"enabled": true
}
}
}Pi needs a separately installed MCP client/extension. In that extension, use
command: uvx and the same argument list. No built-in Pi MCP support or universal
extension config format is claimed. These are configuration examples. This
protocol acceptance tests use the official Python MCP SDK. Host-specific evidence
is recorded separately in the architecture and support boundaries
and the Runtime's client evidence and limits.
Tools and boundaries
Tool | Input | Result |
|
| Scoped memories with IDs, scores and provenance |
|
| Durable memory ID |
| exact | Scoped replacement |
| exact | Scoped deletion |
Scope is fixed by the operator's profile (user_id, agent_id). Model inputs
and MCP client identity cannot override it. Knowing an ID does not grant access.
Migration, export, reset and bulk deletion remain trusted operator CLI commands.
See standalone maintenance.
No resources or prompts are advertised. This is a local subprocess, with no
public HTTP/SSE listener or remote authentication service. Stdout is reserved
for protocol messages, with sanitized diagnostics on stderr.
Data flows from client → Runtime → embedding provider → Qdrant and the local SQLite ledger. With local Ollama and embedded Qdrant, memory processing stays local. Cloud embedding receives memory/query text, and cloud Qdrant receives vectors and stored payloads. The client/model may also receive recalled text. The operator must authorize retention and access and protect the profile files.
One writer lease coordinates a profile/destination. Do not overlap MCP, CLI or Hermes processes writing to it. Separate profiles or machines do not provide a distributed lock. This package does not support uncoordinated multiprocess writes, auto-extraction, an HTTP transport, or implicit credential discovery from Hermes. It preserves the Runtime's ledger, IDs and recovery semantics.
Concepts and evidence
Sharing vs Portability vs Backup: Runtime portability guide
Cross-harness architecture: docs/cross-harness-architecture.md
Shared Owner status: docs/universal-owner-status.md
Validation limits: docs/dsh-validation.md
Validation reports apply to their recorded versions, workloads and host environments. Short protocol or cloud runs do not establish 24-hour acceptance for a new release.
Verification and development
CI builds wheel/sdist, checks metadata and ownership marker. It runs installed protocol tests with temporary profiles, embedded Qdrant and a deterministic loopback embedding fixture on Linux/macOS/Windows, Python 3.11 and 3.14. No test connects to personal Qdrant, Hermes profiles or memory data. These tests cover initialize, discovery, four tools, persistence, recovery, scope isolation, error redaction and protocol stdout. Provider/cloud compatibility evidence belongs to the Runtime.
CI prefers the immutable Runtime PyPI release. Before a Runtime release reaches
PyPI, CI builds a wheel from the immutable revision recorded in runtime-source.json. This is only a preparation fixture:
published dependency metadata always uses the exact PyPI version. Release
workflow acceptance requires installation from PyPI and never uses that fallback.
See CI and dependency maintenance, publishing, architecture, and the optional Skill.
Dependency boundary
The runtime dependency is only hermes-plugin-qdrant-memory[mcp]. The sdist includes the
Python acceptance tests, apart from harnesses that need an external Runtime checkout, DSH
client assets, or Node fixtures the sdist does not carry; selected harness lockfiles and
Node-only .mjs tests are excluded. The wheel remains metadata-only. Development
dependencies are declared under [project.optional-dependencies].dev and are not installed
for end users.
WorkBuddy and DeepSeek Harness
Use the WorkBuddy connector or the
DSH installation guide for explicit durable memory.
Both reuse the Python Runtime, the four MCP tools and the canonical Skill. The published managed launcher prepares private Python
and CPU-model dependencies with Node.js. Thus, the managed routes do not require a
system Python, uvx or Ollama installation. The DSH Bundle is
distributed as @cnkang/qdrant-memory-dsh-bundle. Existing Hermes profiles
and defaults are unchanged. See architecture and version matrix
and validation limits.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory for AI agents: save, search and connect context across tools and sessions.
Persistent memory for AI agents: add, search, update, and delete long-term memories.
Persistent memory, inline redaction, per-agent access, and code localization for AI agents.
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceProvides agents with durable, provenance-aware memory through tools for remembering, recalling, answering, and maintaining information, while structurally resisting injection and confabulation.341 PyPI11MIT
CarpeOS MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to capture, search, and manage structured memory from agent sessions with append-only events and provenance tracking, providing eight local MCP stdio tools.1Apache 2.0- AlicenseNot gradedqualityCmaintenanceEnables agents to read and write a durable, append-only memory with verified provenance, supporting search, record capture, and context preparation across sessions and machines.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to store, recall, and manage persistent memory documents through MCP tools, with authenticated context tokens and hybrid lexical/vector search.MIT