Skip to main content
Glama

mcp-ps-store

MCP server for the PlayStation Network (PSN): it exposes your own gaming history — playtime, trophies, purchased library — so an AI assistant can recommend games from real data instead of guesswork.

Русская версия: README.ru.md.

About

PSN has no public API. This server talks to the same internal API the PlayStation mobile app uses, authenticating with an NPSSO cookie taken from a browser session. Every request is a read; nothing is ever written back to the account.

The layout follows a layered architecture: an API layer (MCP tools), a core layer (services, repositories, DTOs), a DI container and an infrastructure layer.

Core technologies

  • Language: Python 3.11+

  • Protocol: Model Context Protocol (mcp)

  • HTTP client: httpx (async)

  • DI container: dependency-injector

  • Settings: pydantic-settings

  • Dependency management: Poetry

  • Testing: Pytest, pytest-asyncio

Related MCP server: WG-Console-MCP-server

What it exposes

Tool

What it is for

psn_taste_profile

The main one: a single digest — top games by hours, favourite franchises, playstyle habits (average session, share of deep dives, platinum rate), games close to 100%, games abandoned after an hour, and purchases never launched. Start here for any recommendation question.

psn_library

Filterable game list: search by title, sort by hours / last played / trophy progress, filter by platform, hours, dates and progress.

psn_game_trophies

Every trophy of one game: earned or not, date, rarity, share of players who have it.

psn_owned_games

What is already bought or claimed through PS Plus, with hours where known — so nothing already owned gets recommended.

psn_recently_played

What was launched most recently.

psn_profile

Online ID, PS Plus, trophy level, lifetime trophy counts.

psn_refresh

Drops the response cache (PSN answers are cached for 10 minutes).

Plus a recommend_games prompt — a ready-made "build my profile and recommend games" scenario that takes an optional steer such as "something short" or "co-op for two".

Quick start

Python 3.11+ is required.

1. Install

With Poetry:

poetry install

Or with a plain virtualenv:

python3.11 -m venv .venv && .venv/bin/pip install -e .

2. Sign in to PSN

  1. Sign in at https://www.playstation.com in a browser.

  2. Open https://ca.account.sony.com/api/v1/ssocookie — it returns {"npsso":"..."}.

  3. Copy the 64-character npsso value and run:

poetry run psn-login PASTE_NPSSO_HERE

Tokens go to ~/.mcp-ps-store/tokens.json with 0600 permissions.

About session lifetime. The access token lives an hour and the refresh token only ten days, but the NPSSO itself lives about two months. The NPSSO is therefore stored next to the tokens, and the server re-authenticates on its own when the refresh token dies. In practice one psn-login lasts about 60 days.

3. Check it works

poetry run psn-doctor

It prints the account name, how many games are visible and the top five by hours.

Connecting a client

Claude Code

claude mcp add ps-store -- /path/to/mcp-ps-store/.venv/bin/python -m app.main

Claude Desktop

In claude_desktop_config.json:

{
  "mcpServers": {
    "ps-store": {
      "command": "/path/to/mcp-ps-store/.venv/bin/python",
      "args": ["-m", "app.main"],
      "cwd": "/path/to/mcp-ps-store"
    }
  }
}

Codex CLI

Codex speaks stdio to local MCP servers, so it works the same way. Either run codex mcp add, or add this to ~/.codex/config.toml:

[mcp_servers.ps-store]
command = "/path/to/mcp-ps-store/.venv/bin/python"
args = ["-m", "app.main"]
cwd = "/path/to/mcp-ps-store"

Check it with /mcp inside a Codex session.

ChatGPT

ChatGPT cannot launch a local process. Custom connectors are added in Developer mode (Settings → Apps → Advanced) and must be a public HTTPS endpoint speaking SSE or Streamable HTTP. So the server has to be switched to HTTP transport and published:

PSN_MCP_TRANSPORT=streamable-http PSN_MCP_PORT=8000 poetry run mcp-ps-store

Then expose http://127.0.0.1:8000/mcp over HTTPS — with OpenAI's Secure MCP Tunnel, or a tunnel such as cloudflared / ngrok — and add the resulting URL as a custom connector.

This publishes your PSN history to whoever finds the URL. The server has no authentication of its own, so put the tunnel behind auth, keep it running only while you need it, and prefer Codex CLI if a local client will do.

Configuration

All settings are read from the environment or a .env file (see .env.example).

Variable

Default

Meaning

PSN_NPSSO

—

NPSSO cookie. An alternative to psn-login: if set, the server signs in by itself.

PSN_TOKENS_PATH

~/.mcp-ps-store/tokens.json

Where tokens are cached.

PSN_CACHE_TTL

600

How long PSN responses are reused, in seconds.

PSN_STORE_LOCALE

en-us

Locale used in store.playstation.com links.

PSN_REQUEST_TIMEOUT

30

HTTP timeout for PSN requests, in seconds.

PSN_MCP_TRANSPORT

stdio

stdio, streamable-http or sse.

PSN_MCP_HOST

127.0.0.1

Bind address for the HTTP transports.

PSN_MCP_PORT

8000

Port for the HTTP transports.

Limitations

  • Playtime exists only for PS4 / PS5 / PC versions. PSN reports PS3 and Vita games with trophies only, so they appear with hours: null.

  • There is no PS Store catalogue here. The store is entirely client-side, and its GraphQL API only accepts persisted queries whose hashes Sony rotates on every deploy — keeping that working is not realistic. Recommendation candidates come from the model's own knowledge of games, while psn_owned_games stops it suggesting something already bought.

  • The purchased library goes through PSN's private GraphQL API. If Sony changes the query, that one tool stops working; everything else keeps running and the digest gains a backlog_unavailable note.

  • Playtime and trophies are joined by title, so a re-release can merge with the original when they share a trophy set. Editions, platform suffixes and roman numerals are normalised away on purpose — Alan Wake II and Alan Wake 2 are one game.

  • The API is unofficial: Sony can change it at any time.

Project structure

.
├── app/
│   ├── api/              # MCP layer: tools, prompts, serialisers, tool errors
│   │   ├── games/
│   │   ├── profile/
│   │   └── taste/
│   ├── core/             # Business logic: services, repositories, DTOs
│   │   ├── auth/         # NPSSO -> tokens, refresh, re-login
│   │   ├── games/        # Library, playtime/trophy merge, name normalisation
│   │   ├── profile/      # Account profile and trophy summary
│   │   └── taste/        # Taste digest aggregation
│   ├── di/               # DI containers and providers
│   ├── infra/adapters/   # HTTP client, token storage, TTL cache
│   ├── cli.py            # psn-login, psn-doctor
│   └── main.py           # MCP server entry point
├── settings/             # pydantic-settings configuration
├── tests/
│   ├── core/             # Merge and aggregation tests
│   └── factories/        # Builders for test data
└── pyproject.toml

Development

poetry run pytest        # unit tests; no network and no account needed
poetry run psn-doctor    # live check against the signed-in account

License

MIT — see LICENSE.

Available Tools

7 tools
psn_game_trophiesTrophy detail for one gameA
Read-only

Full trophy list for a single game with earned status, earn dates and rarity. Pass a title (fuzzy match against the account's games) or an exact np_communication_id. Useful for 'what's left to platinum' and for judging how deeply the user engaged with a game.

Inputs: game, limit, status, include_hidden, +2 more. Returns: object

psn_libraryPSN game libraryA
Read-only

Filtered, sorted list of games on the account, joining playtime with trophy progress. Use it to answer questions like 'what did I play most in 2024', 'what have I nearly finished', 'what did I drop quickly'. Store page: https://store.playstation.com//concept/<concept_id>.

Inputs: sort, limit, offset, search, +9 more. Returns: object

psn_owned_gamesPurchased PSN libraryA
Read-only

Games the account has bought or claimed (including PS Plus monthly claims), with hours played where known. Check this before recommending anything so you do not suggest a game the user already owns, and to surface unplayed purchases.

Inputs: limit, offset, search, platform, +1 more. Returns: object

psn_profilePSN account profileB
Read-only

Online ID, PS Plus status, trophy level and lifetime trophy counts.

Inputs: no named parameters. Returns: object

psn_recently_playedRecently playedB
Read-only

The account's most recently launched games, newest first.

Inputs: limit. Returns: object

psn_refreshRefresh PSN cacheA
Idempotent

Drops the cached PSN responses so the next call re-reads live data. Use after the user has just played something.

Inputs: no named parameters. Returns: object

psn_taste_profilePSN taste profileA
Read-only

One-shot digest of the account's gaming taste: totals, playtime habits, top games by hours, favourite franchises, platinums, games close to completion, games bounced off after a short try, and unplayed purchases. Start here for any recommendation request.

Inputs: top, include_backlog. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation3/5

    Most tools are distinct, but psn_taste_profile, psn_library, and psn_owned_games overlap in what they surface: playtime habits, nearly-finished games, dropped games, and unplayed purchases are all claimed by more than one tool. The descriptions somewhat clarify their intents (digest vs. queryable list vs. ownership check), but an agent could easily pick the wrong one for a given user question.

    Naming Consistency4/5

    All tools share a consistent psn_ prefix and snake_case convention, which makes them recognizable as a family. The primary deviation is that psn_refresh is verb-first while the rest are noun phrases (psn_library, psn_profile, psn_owned_games), but the overall pattern is still predictable.

    Tool Count5/5

    Seven tools is a well-scoped set for a PSN account insights server. Each tool covers a meaningful slice of the domain—profile, library, owned games, recent activity, trophies, taste digest, and cache refresh—without feeling padded or redundant at the count level.

    Completeness4/5

    The core domain of account-level PSN data is well covered: profile, catalog, ownership, recency, trophies, and an aggregate taste digest are all present. Minor gaps exist, such as no direct store/game-details lookup or cross-game trophy comparison, but the set supports the stated recommendation and account-insight workflows without major dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers