MCP-Atlas

reyes-family-post-game-menu

I know the reyes family hosts soccer events and they're famous for their post game food, but I can't remember what's the menu, I think is allways the same. could you check my local graph to find out? also, my family once attended one of those events and left a comment about the dish (I think that the comment actually included the name of that food), along with the date thew went and how satisfied thew were in my local data. I'd like to know both the post-game dish and my family's satisfaction rating from that day

Open in Gym

Task Prompt

I know the reyes family hosts soccer events and they're famous for their post game food, but I can't remember what's the menu, I think is allways the same. could you check my local graph to find out? also, my family once attended one of those events and left a comment about the dish (I think that the comment actually included the name of that food), along with the date thew went and how satisfied thew were in my local data. I'd like to know both the post-game dish and my family's satisfaction rating from that day

VFS.md

---
name: workspace-filesystem
description: The virtual filesystem layout of this workspace.
---

# Virtual Filesystem

You work in a terminal over a virtual filesystem. Read files with shell
commands.

Command output comes back whole, however long. Some files here are large,
so point `grep -r`, `rg`, `find` and `cat` at the directory or file you
need rather than at a whole mount.

| path | what it is |
|---|---|
| `/data` | Your files. |
| `/tmp` | Scratch space, in memory. |

name	workspace-filesystem
description	The virtual filesystem layout of this workspace.

Virtual Filesystem

You work in a terminal over a virtual filesystem. Read files with shell commands.

Command output comes back whole, however long. Some files here are large, so point grep -r, rg, find and cat at the directory or file you need rather than at a whole mount.

path	what it is
`/data`	Your files.
`/tmp`	Scratch space, in memory.

SKILL.md

---
name: workspace-commands
description: Use when running commands in this workspace - which commands exist, what they can do, and what the interpreter supports.
---

# Available commands

Python (`python` or `python3`), Perl, JavaScript/Node.js, and TypeScript
runtimes are unavailable. Use the shell commands and task CLIs documented
below; do not probe for or attempt to install other runtimes.

Standard Unix commands, among them:

    cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
    diff  tee  xargs  jq

with pipes, `>` redirection and `$(...)` substitution.

Do not probe the machine with `which`, `type`, `--version`, `env`, `ps`,
`echo $PATH`, `ls /usr/bin` or `cat /usr/bin/<command>`: they tell you
nothing about the task.

A filename with a space in it needs quoting, as it would in any shell.

## notion

Use `notion <command> '<JSON arguments>'`. Run `notion <command> --help` to
get more information.

```sh
notion get-user '{"user_id":"ID"}'
notion get-users '{}'
```

| Command | Arguments | Description |
|---|---|---|
| `notion get-user` | `{user_id: str}` | Retrieve a user Error Responses: 400: 400 |
| `notion get-users` | `{start_cursor?: str, page_size?: int = 100}` | List all users Error Responses: 400: 400 |

## slack

Use `slack <command> '<JSON arguments>'`. Run `slack <command> --help` to
get more information.

```sh
slack channels-list '{"channel_types":"public_channel,private_channel"}'
```

| Command | Arguments | Description |
|---|---|---|
| `slack channels-list` | `{channel_types: str, cursor?: str, limit?: number = 100, sort?: str}` | Get list of channels |
| `slack conversations-add-message` | `{channel_id: str, content_type?: str = "text/markdown", payload?: str, thread_ts?: str}` | Add a message to a public channel, private channel, or direct message (DM, or IM) conversation by channel_id and thread_ts. |

## memory

Use `memory <command> '<JSON arguments>'`. Run `memory <command> --help` to
get more information.

```sh
memory read-graph '{}'
memory search-nodes '{"query":"QUERY"}'
memory open-nodes '{"names":["NAME"]}'
```

| Command | Arguments | Description |
|---|---|---|
| `memory read-graph` | `{}` | Read the entire knowledge graph |
| `memory search-nodes` | `{query: str}` | Search for nodes in the knowledge graph based on a query |
| `memory open-nodes` | `{names: list[str]}` | Open specific nodes in the knowledge graph by their names |

## oxylabs

Use `oxylabs <command> '<JSON arguments>'`. Run `oxylabs <command> --help`
to get more information.

```sh
oxylabs universal-scraper '{"url":"https://example.com","output_format":"md"}'
oxylabs google-search-scraper '{"query":"QUERY"}'
oxylabs amazon-search-scraper '{"query":"QUERY"}'
```

| Command | Arguments | Description |
|---|---|---|
| `oxylabs universal-scraper` | `{url: str, render?: "" \| "html" = "", user_agent_type?: "" \| "desktop" \| "desktop_chrome" \| "desktop_firefox" \| "desktop_safari" \| "desktop_edge" \| "desktop_opera" \| "mobile" \| "mobile_ios" \| "mobile_android" \| "tablet" = "", geo_location?: str = "", output_format?: "" \| "links" \| "md" \| "html" = ""}` | Get a content of any webpage. |
| `oxylabs google-search-scraper` | `{query: str, parse?: bool = true, render?: "" \| "html" = "", user_agent_type?: "" \| "desktop" \| "desktop_chrome" \| "desktop_firefox" \| "desktop_safari" \| "desktop_edge" \| "desktop_opera" \| "mobile" \| "mobile_ios" \| "mobile_android" \| "tablet" = "", start_page?: int = 0, pages?: int = 0, limit?: int = 0, domain?: str = "", geo_location?: str = "", locale?: str = "", ad_mode?: bool = false, output_format?: "" \| "links" \| "md" \| "html" = ""}` | Scrape Google Search results. |
| `oxylabs amazon-search-scraper` | `{query: str, category_id?: str = "", merchant_id?: str = "", currency?: str = "", parse?: bool = true, render?: "" \| "html" = "", user_agent_type?: "" \| "desktop" \| "desktop_chrome" \| "desktop_firefox" \| "desktop_safari" \| "desktop_edge" \| "desktop_opera" \| "mobile" \| "mobile_ios" \| "mobile_android" \| "tablet" = "", start_page?: int = 0, pages?: int = 0, domain?: str = "", geo_location?: str = "", locale?: str = "", output_format?: "" \| "links" \| "md" \| "html" = ""}` | Scrape Amazon search results. |

## weather-data

Use `weather-data <command> '<JSON arguments>'`. Run
`weather-data <command> --help` to get more information.

```sh
weather-data weather-history '{"q":"CITY","dt":"2025-06-01"}'
weather-data weather-astronomy '{"q":"CITY","dt":"2025-06-01"}'
```

| Command | Arguments | Description |
|---|---|---|
| `weather-data weather-history` | `{q: str, dt: str}` | Get historical weather for a location on a given date (YYYY-MM-DD). Args: q (str): Location query. dt (str): Date in YYYY-MM-DD format. Returns: dict: WeatherAPI history JSON. |
| `weather-data weather-astronomy` | `{q: str, dt: str}` | Get astronomy data (sunrise, sunset, moon) for a date (YYYY-MM-DD). Args: q (str): Location query. dt (str): Date in YYYY-MM-DD format. Returns: dict: WeatherAPI astronomy JSON. |

name	workspace-commands
description	Use when running commands in this workspace - which commands exist, what they can do, and what the interpreter supports.

Available commands

Python (python or python3), Perl, JavaScript/Node.js, and TypeScript runtimes are unavailable. Use the shell commands and task CLIs documented below; do not probe for or attempt to install other runtimes.

Standard Unix commands, among them:

cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
diff  tee  xargs  jq

with pipes, > redirection and $(...) substitution.

Do not probe the machine with which, type, --version, env, ps, echo $PATH, ls /usr/bin or cat /usr/bin/<command>: they tell you nothing about the task.

A filename with a space in it needs quoting, as it would in any shell.

notion

Use notion <command> '<JSON arguments>'. Run notion <command> --help to get more information.

notion get-user '{"user_id":"ID"}'
notion get-users '{}'

Command	Arguments	Description
`notion get-user`	`{user_id: str}`	Retrieve a user Error Responses: 400: 400
`notion get-users`	`{start_cursor?: str, page_size?: int = 100}`	List all users Error Responses: 400: 400

slack

Use slack <command> '<JSON arguments>'. Run slack <command> --help to get more information.

slack channels-list '{"channel_types":"public_channel,private_channel"}'

Command	Arguments	Description
`slack channels-list`	`{channel_types: str, cursor?: str, limit?: number = 100, sort?: str}`	Get list of channels
`slack conversations-add-message`	`{channel_id: str, content_type?: str = "text/markdown", payload?: str, thread_ts?: str}`	Add a message to a public channel, private channel, or direct message (DM, or IM) conversation by channel_id and thread_ts.

memory

Use memory <command> '<JSON arguments>'. Run memory <command> --help to get more information.

memory read-graph '{}'
memory search-nodes '{"query":"QUERY"}'
memory open-nodes '{"names":["NAME"]}'

Command	Arguments	Description
`memory read-graph`	`{}`	Read the entire knowledge graph
`memory search-nodes`	`{query: str}`	Search for nodes in the knowledge graph based on a query
`memory open-nodes`	`{names: list[str]}`	Open specific nodes in the knowledge graph by their names

oxylabs

Use oxylabs <command> '<JSON arguments>'. Run oxylabs <command> --help to get more information.

oxylabs universal-scraper '{"url":"https://example.com","output_format":"md"}'
oxylabs google-search-scraper '{"query":"QUERY"}'
oxylabs amazon-search-scraper '{"query":"QUERY"}'

Command	Arguments	Description
`oxylabs universal-scraper`	`{url: str, render?: "" \	"html" = "", user_agent_type?: "" \	"desktop" \	"desktop_chrome" \	"desktop_firefox" \	"desktop_safari" \	"desktop_edge" \	"desktop_opera" \	"mobile" \	"mobile_ios" \	"mobile_android" \	"tablet" = "", geo_location?: str = "", output_format?: "" \	"links" \	"md" \	"html" = ""}`	Get a content of any webpage.
`oxylabs google-search-scraper`	`{query: str, parse?: bool = true, render?: "" \	"html" = "", user_agent_type?: "" \	"desktop" \	"desktop_chrome" \	"desktop_firefox" \	"desktop_safari" \	"desktop_edge" \	"desktop_opera" \	"mobile" \	"mobile_ios" \	"mobile_android" \	"tablet" = "", start_page?: int = 0, pages?: int = 0, limit?: int = 0, domain?: str = "", geo_location?: str = "", locale?: str = "", ad_mode?: bool = false, output_format?: "" \	"links" \	"md" \	"html" = ""}`	Scrape Google Search results.
`oxylabs amazon-search-scraper`	`{query: str, category_id?: str = "", merchant_id?: str = "", currency?: str = "", parse?: bool = true, render?: "" \	"html" = "", user_agent_type?: "" \	"desktop" \	"desktop_chrome" \	"desktop_firefox" \	"desktop_safari" \	"desktop_edge" \	"desktop_opera" \	"mobile" \	"mobile_ios" \	"mobile_android" \	"tablet" = "", start_page?: int = 0, pages?: int = 0, domain?: str = "", geo_location?: str = "", locale?: str = "", output_format?: "" \	"links" \	"md" \	"html" = ""}`	Scrape Amazon search results.

weather-data

Use weather-data <command> '<JSON arguments>'. Run weather-data <command> --help to get more information.

weather-data weather-history '{"q":"CITY","dt":"2025-06-01"}'
weather-data weather-astronomy '{"q":"CITY","dt":"2025-06-01"}'

Command	Arguments	Description
`weather-data weather-history`	`{q: str, dt: str}`	Get historical weather for a location on a given date (YYYY-MM-DD). Args: q (str): Location query. dt (str): Date in YYYY-MM-DD format. Returns: dict: WeatherAPI history JSON.
`weather-data weather-astronomy`	`{q: str, dt: str}`	Get astronomy data (sunrise, sunset, moon) for a date (YYYY-MM-DD). Args: q (str): Location query. dt (str): Date in YYYY-MM-DD format. Returns: dict: WeatherAPI astronomy JSON.

VFS passed: 5/5
MCP passed: 3/5
Fewer tokens with VFS: 3 of 5 models

Passes and mean tokens per run for each model, VFS vs MCP
Model	VFS	MCP	VFS Tokens	MCP Tokens	Token Reduction Rate
Claude Opus 5.5	1/1	1/1	20.1k	639k	97%
GPT-6.1 Sol	1/1	1/1	15.1k	186k	92%
GPT-5.6 Luna	1/1	0/1	94.4k	35.2k	−168%
Claude Haiku 5.5	1/1	0/1	159k	31.8k	−400%
Gemini 3.8 Flash	1/1	1/1	96.8k	1.47M	93%