Does Qdrant MCP work with ChatGPT (Codex)?

Q: Does Qdrant MCP work with ChatGPT (Codex)?

Yes. In our test on 2026-10-20 (Codex CLI 0.162.0-alpha.17.2, mcp-server-qdrant 0.8.1, plan: ChatGPT Plus), Qdrant MCP passed install, connect, tools and an agent task.

Yes. Qdrant MCP passed every step of our test in ChatGPT (Codex) on Oct 20, 2026: it installed, connected, its tools were visible, and an agent used it to finish a real task.

Result

ResultPassed

Date testedOct 20, 2026

Plan tested onChatGPT Plus

App versionCodex CLI 0.162.0-alpha.17.2

Server packagemcp-server-qdrant 0.8.1

Connect timeconnect time not recorded

Modelgpt-6-luna (reasoning low)

Steps

install OK
connect OK
tools visible OK
agent task: roundtrip OKwrite then read back from a local database/vector store (no cloud account)

From our own harness run, not the maker’s claims. How we test.

Versions tested

Codex CLI 0.162.0-alpha.17.2 · mcp-server-qdrant 0.8.1 · connect time not recorded · tested Oct 20, 2026

Server package tested: mcp-server-qdrant 0.8.1 (uv, Python 3.12.15; resolved 2026-10-20)

Direct and key dependencies as resolved: anyio 4.15.1 · fastembed 0.9.0 · fastmcp 2.7.0 · httpx 0.28.1 · mcp 1.30.0 · pydantic 2.11.10 · pydantic-settings 2.16.1 · pydantic_core 2.33.2 · qdrant-client 1.19.1 · sse-starlette 3.5.0 · starlette 1.9.0 · typing_extensions 4.16.0 · uvicorn 0.54.0

All 67 resolved dependencies

annotated-doc==0.0.5
annotated-types==0.8.0
anyio==4.15.1
attrs==26.1.0
Authlib==1.9.1
certifi==2026.10.19
cffi==2.1.1
charset-normalizer==3.5.2
click==8.5.0
cryptography==50.0.2
exceptiongroup==1.3.1
fastembed==0.9.0
fastmcp==2.7.0
filelock==4.2.4
flatbuffers==25.12.19
fsspec==2026.9.0
grpcio==1.84.0
h11==0.16.0
h2==4.4.1
hf-xet==1.7.0
hpack==4.2.0
httpcore==1.0.9
httpx==0.28.1
httpx-sse==0.4.3
huggingface_hub==1.33.0
hyperframe==6.1.0
idna==3.20
joserfc==1.7.7
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
loguru==0.7.3
markdown-it-py==4.2.0
mcp==1.30.0
mdurl==0.1.2
mmh3==5.3.1
numpy==2.5.4
onnxruntime==1.31.0
openapi-pydantic==0.6.0
packaging==26.3
pillow==12.3.0
portalocker==3.2.0
protobuf==7.36.2
py_rust_stemmers==0.1.8
pycparser==3.11
pydantic==2.11.10
pydantic-settings==2.16.1
pydantic_core==2.33.2
Pygments==2.21.0
PyJWT==2.15.1
python-dotenv==1.2.4
python-multipart==0.0.32
PyYAML==6.0.3
qdrant-client==1.19.1
referencing==0.37.0
requests==2.34.2
rich==15.0.0
rpds-py==2026.9.1
shellingham==1.5.4
sse-starlette==3.5.0
starlette==1.9.0
tokenizers==0.23.3
tqdm==4.70.1
typer==0.27.3
typing-inspection==0.4.4
typing_extensions==4.16.0
urllib3==2.8.0
uvicorn==0.54.0

Captured with: uvx --from mcp-server-qdrant python (importlib.metadata in the same uvx env; equivalent to uv pip freeze).

What happened in this run

Install config we used

[mcp_servers.qdrant]
command = "uvx"
args = ["mcp-server-qdrant"]
env = {QDRANT_LOCAL_PATH="{SANDBOX}/qdrant",COLLECTION_NAME="toolpassed"}

Connection check

server answered tool calls during the task

Tools check

verified via task step: agent saw and called the server's tools

Agent task: roundtrip

Tool calls, in order: qdrant:qdrant-store, qdrant:qdrant-find

Raw details from our harness log for this run. Secrets redacted.

Set it up in ChatGPT (Codex)

Copy-paste config for every app is on the Qdrant MCP page. Not connecting? ChatGPT (Codex) MCP troubleshooting.

Other apps we tested it in: Claude Code (passed) · Cursor (passed) · Claude Desktop (passed).

All MCP servers tested in ChatGPT (Codex)