Skip to content

SandBase MCP server

io.github.sandbaseai/clisandbaseaistreamable-httpv0.3.10Scanned

Connect MCP clients to 2,000+ AI models without managing provider API keys.

7 tools: 2 can delete or cancel things, 3 change things and 2 only read.

Tools: 2 delete, 0 irreversible, 3 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the SandBase MCP server can do

The SandBase MCP server is published by the GitHub account sandbaseai. It has 7 tools. It can delete or cancel things (2 tools: sandbase_run_cancel and sandbase_run) and create or change data (3 tools: sandbase_run_get, sandbase_runs and sandbase_account). 2 tools only read.

2 tools bring in text other people can write (sandbase_run_cancel and sandbase_run).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 0.3.10.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Deletes or cancels 2Claude Code: deny
  • sandbase_runExecute a model, API, or Agent Service.Reads text others writeNo findings

    Why it is in this group

    • The name "sandbase_run" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Execute a model, API, or Agent Service. Sync models return the result directly; async models (image/video/audio jobs) return status running with a run_id — poll sandbase_run_get for the output. Services require arguments.idempotency_key and optionally input; reuse the same key and input on retries. Service acceptance is not completion: poll sandbase_run_get with service_id and run_id. Omit the MCP task parameter for Services.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • sandbase_run_cancelRequest cancellation of an Agent Service run; inspect its status afterward.Reads text others writeNo findings

    Why it is in this group

    • The name "sandbase_run_cancel" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Request cancellation of an Agent Service run; inspect its status afterward.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
Changes things 3Claude Code: ask
  • sandbase_accountCheck your SandBase account balance.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check your SandBase account balance. This call is not billed. Use before expensive operations.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • sandbase_run_getGet async run status and results.1 finding

    Why it is in this group

    • The name "sandbase_run_get" says "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "sandbase_run_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "sandbase_run_get" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Get async run status and results. For Agent Services supply both service_id and run_id; succeeded, failed, and cancelled are terminal. Session items are paginated: use cursor for subsequent pages; items_available=false means retry output retrieval. Model runs use completed or failed.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • sandbase_runsList recent model/API calls, or supply service_id to list runs of an Agent Service.1 finding

    Why it is in this group

    • The name "sandbase_runs" says "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "sandbase_runs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "sandbase_runs" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    List recent model/API calls, or supply service_id to list runs of an Agent Service.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
Only reads 2Show 2 read-only tools
  • sandbase_discoverFind a model, API, or Agent Service for the task.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find a model, API, or Agent Service for the task. Call this proactively before writing a scraper, before a generic web fetch for structured data, before telling the user something is inaccessible, and whenever you need image/video/music/speech generation, social media data, search results, web scraping, product/company/people data, embeddings, or a specific third-party model. Supports keyword search (q), type filtering (llm/api/multimodal/embedding/service), and vendor filtering. Discovery is not billed; start here.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • sandbase_inspectInspect a model, API, or Agent Service: input schema, available pricing, and an execution template.No findings

    Why it is in this group

    • The name "sandbase_inspect" says "inspect": a word for reading.
    Description, as the server wrote it
    Inspect a model, API, or Agent Service: input schema, available pricing, and an execution template. Service names are svc_ IDs. Always inspect before running.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (2 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.sandbase.ai/v1/mcp: tools/list returned 7 tools to an anonymous client, including sandbase_run_cancel (destructive), sandbase_run (destructive), sandbase_run_get (write), sandbase_runs (write), sandbase_account (write)

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 5
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "sandbase_run_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "sandbase_run_get" says "run": a word for a change.

    What this check looks for
  • The server marks "sandbase_runs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "sandbase_runs" says "run": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 5 (and 2 more).View diff
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 5
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed

Install

Pinned to version 0.3.10. Values in angle brackets are yours to fill in.

claude mcp add --transport http cli https://api.sandbase.ai/v1/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http cli https://api.sandbase.ai/v1/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__cli__sandbase_discover",
      "mcp__cli__sandbase_inspect"
    ],
    "ask": [
      "mcp__cli__sandbase_run_get",
      "mcp__cli__sandbase_runs",
      "mcp__cli__sandbase_account"
    ],
    "deny": [
      "mcp__cli__sandbase_run_cancel",
      "mcp__cli__sandbase_run"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as cli. Review it before you use it.

Capability tags behind 2 rules
  • mcp__cli__sandbase_run_cancel untrusted-input
  • mcp__cli__sandbase_run untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.sandbaseai/cli/verify?hash=c09d3fecc375263a5a422eef9e9e27c631930be9732a2501c6e88b09cba41e1d" | jq -e '.changed == false'

Pinned hash c09d3fecc375, from Nov 11, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.sandbaseai/cli/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.sandbaseai/cli
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.sandbaseai/cli.svg)](https://radar.anlyon.com/servers/io.github.sandbaseai/cli)

Source: MCP Registry · repository. Synced Nov 11, 2026, 06:18 UTC.

SandBase MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the SandBase MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the SandBase MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: sandbase_run_cancel and sandbase_run.

Can the SandBase MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the SandBase MCP server have?

7 tools: 2 destructive, 3 write, 2 read. sandbase_run_cancel, sandbase_run, sandbase_run_get, sandbase_runs, sandbase_account, sandbase_discover and sandbase_inspect.

Does the SandBase MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the SandBase MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the SandBase MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.