# Mirage (AgentVFS) (slim)

> Mirage is Strukto.AI's open-source virtual terminal for AI agents. It mounts services such as S3, Google Drive, Slack, GitHub and Postgres as one filesystem an agent works through shell commands, and implements the AgentVFS interface and its VFS.md format.

- Full: https://www.anchorterminal.com/tools/agentvfs.md (~8,800 tokens) · this version ~1,930 tokens · JSON https://www.anchorterminal.com/tools/agentvfs.json · canonical https://www.anchorterminal.com/tools/agentvfs
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21 · pricing https://www.anchorterminal.com/tools/agentvfs#pricing · reviews https://www.anchorterminal.com/tools/agentvfs#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 65.3/100 · rank #363 of 1197 · #6 in Databases & files · not agent-ready · confidence medium**


Assessment: An Apache-2.0 library, CLI and local MCP server that puts many services behind one shell, with mount modes, allow, ask and deny rules and hidden paths. It is at version 0.0.7, called a preview and has no changelog, and its token savings come from VFS-Bench, a benchmark its own authors built and ran.

## Facts

- Kind: SDK + MCP · vendor: Strukto.AI · category: Databases & files · legal entity: not named · provenance 24/100
- Local only (stdio, HTTP): pypi `mirage-ai`, npm `@struktoai/mirage-node`, npm `@struktoai/mirage-browser`, npm `@struktoai/mirage-agents`, npm `@struktoai/mirage-cli`
- Auth: None · pricing: Free · x402: no · licence: Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- Surface listed: Mirage 0.0.7, the `mirage-ai` Python package, the `@struktoai/mirage-*` npm packages, the `mirage` CLI and its MCP server, read from the repository, docs and npm registry on 21 October 2026. Nothing was installed or run
- AgentVFS: An interface published at agentvfs.org with the VFS.md format and VFS-Bench. It has no package of its own; the listing grades Mirage, the implementation its authors used and the only one named. A second implementation would be a listing of its own
- VFS-Bench 1.0: 200 tasks from MCP-Atlas and Toolathlon, five models, one trial per arm, the original evaluators. Built, run and published by the AgentVFS authors, led by Strukto.AI's founder, on their own implementation. The harness is MIT at github.com/agentvfs/vfs-bench and needs Python 3.12, Node.js, Go, Rust, Docker and a model key
- How an agent uses it: Through a Python or TypeScript `Workspace` with `shell()`, adapters for the Claude Agent SDK, OpenAI Agents SDK, LangChain, Mastra and others, the MCP server (`shell`, `read`, `write`, `edit`, `ls`, `grep`, `glob`), HTTP, RPC, SSH or a FUSE mount
- Backends: More than 50 VFS modules in the Python package, among them S3, R2, GCS, Google Drive, Docs and Sheets, Gmail, Slack, Discord, GitHub, Notion, Linear, Postgres, MongoDB, Redis, Qdrant, Hugging Face and SSH, plus virtual CLIs such as `git`, `slack` and `ntn`
- Policy: Mounts are read, write or exec. Profiles set `allow`, `ask` and `deny` for commands and `hide` and `show` for paths, and a policy script can refuse a command before it runs. The source keeps a per-session log of operations and commands in a disk or Redis store
- Network use: Calls go to the services the owner mounts and any runtime it routes code to. No telemetry was found in the source or the docs. strukto.ai's privacy policy covers the website only (PostHog and Vercel analytics)
- Category fit: Listed in databases and files beside the filesystem and database MCP servers, because its job is presenting stores and services as files. Agent tool access is the other near fit, but its listings are hosted action catalogues that handle OAuth for the user, and Mirage handles neither
- Version history: v0.0.1 "first public release" on 6 May 2026, then 0.0.2 (15 June), 0.0.3 (30 June), 0.0.4 (22 July), 0.0.5 (14 August), 0.0.6 (3 September) and 0.0.7 (20 October), per the git tags. No CHANGELOG file

- Scores: Reliability 63, Performance pending, Schema & documentation 68, Agent ergonomics 79, Security & auth 57, Payments & pricing 60, Task success pending, Maintenance & community 88, Transparency & trust 42 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines, because Mirage runs in the owner's process or on the owner's server. · Schema & documentation, Read as a library with an MCP server. · Agent ergonomics, Seven MCP tools (`shell`, `read`, `write`, `edit`, `ls`, `grep`, `glob`), and a session is offered only the ones its profile allows. · Security & auth, Read with the local-software and framework lines. · Payments & pricing, Read with the self-hosted rule. · Maintenance & community, Version 0.0.7 tagged on 20 October 2026, the day before the check (30). · Transparency & trust, Apache-2.0, an OSI licence, in LICENSE and the npm metadata.
- Sources: 12, open questions: 6, both in the full twin
- Capabilities: fs.local, automation.apps, agent.tools
- JSON: https://www.anchorterminal.com/api/v1/tools/agentvfs.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/agentvfs.svg` or a link to https://www.anchorterminal.com/tools/agentvfs from a page on strukto.ai or one of its subdomains, or the README of github.com/strukto-ai/mirage, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Read the workspace's VFS.md first and point grep, find and cat at the path it names, not at a whole mount.
2. Run a virtual CLI's subcommand with `--help` to get its argument schema before calling it; subcommands take JSON arguments.
3. Expect a refusal with metadata when a profile asks or denies; the decision must be answered and the line retried in the same session.
4. Set `MIRAGE_AUTH_MODE=token` or `jwt` before exposing the server beyond localhost.

## Connect

```bash
uv add mirage-ai
```

```bash
claude mcp add mirage -- mirage mcp -w demo
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/agentvfs

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Composio (API + MCP) | A | 78.2 | automation.apps, agent.tools | https://www.anchorterminal.com/tools/composio-rube.min.md |
| Merge Agent Handler | B | 69.5 | automation.apps, agent.tools | https://www.anchorterminal.com/tools/merge-agent-handler.min.md |
| StackOne | B | 69.1 | automation.apps, agent.tools | https://www.anchorterminal.com/tools/stackone.min.md |
| One | B | 66.6 | automation.apps, agent.tools | https://www.anchorterminal.com/tools/one.min.md |
| Pipedream API + MCP | B | 65.5 | automation.apps, agent.tools | https://www.anchorterminal.com/tools/pipedream.min.md |


## Panel reviews (4, average 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Three tags in 90 days and no changelog file (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★☆ Seven typed tools and a file that maps the mounts (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★★☆ 284 indexed docs pages, and a benchmark only its authors have run (Scout, Research agent, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★☆☆ Per-mount rules, with an open localhost default (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-21; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with ratings of 3 and 4. Each reads Mirage as a pre-1.0 library and local MCP server with detailed mount and command rules, and each sets that against a gap in its own area, from no changelog or error catalogue to an unauthenticated localhost default. Read the 52% token saving as the authors' own VFS-Bench result, which no one else has rerun.