Agent Toolbox MCP server
io.github.johngee518/agenttoolboxjohngee518streamable-httpv1.0.0Scanned
Free, no-key MCP server: token estimates, JSON Schema conversion, MCP configs, tool search.
4 tools: 3 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 Agent Toolbox MCP server can do
The Agent Toolbox MCP server is published by the GitHub account johngee518. It has 4 tools. It can create or change data (3 tools: estimate_tokens, convert_schema and mcp_config), but cannot delete data. 1 tool only reads.
1 tool reads private data (search_directory); 1 tool can send data out of your system (mcp_config).
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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.0.0.
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.
4 tools
Changes things 3Claude Code: ask
convert_schemaTurn one JSON Schema into OpenAI, Anthropic, and MCP tool definitions with the same name and description.1 finding
Why it is in this group
- The name "convert_schema" says "convert": 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 "convert_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "convert_schema" says "convert": a word for a change.
Description, as the server wrote it Turn one JSON Schema into OpenAI, Anthropic, and MCP tool definitions with the same name and description. It rewrites the envelope only. It does not validate that the schema is a good tool description.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_tokensEstimate input tokens for a text and the USD list-price cost across the models in the Agent Toolbox price table (verified 2026-11-18).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 Estimate input tokens for a text and the USD list-price cost across the models in the Agent Toolbox price table (verified 2026-11-18). The count is a rough heuristic (about 4 characters or 1.3 words per token), not a provider tokenizer. Use it to compare models before a run. It does not call a model.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mcp_configBuild a generic mcpServers JSON object for one local stdio command or one remote URL.Can send data out1 finding
Why it is in this group
- The input takes a statement or command to run (input.command), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "mcp_config" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.command), which can change anything it can reach.
Description, as the server wrote it Build a generic mcpServers JSON object for one local stdio command or one remote URL. Client-specific files (Claude Code type, VS Code servers, Codex TOML) are documented on /tools/mcp. This tool does not contact the server.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
search_directorySearch the hand-curated Agent Toolbox directory by words and category.Reads private dataNo findings
Why it is in this group
- The name "search_directory" says "search": a word for reading.
What it can reach
- private-dataThe name "search_directory" says "search" and "directory": it reads files.
- private-dataThe description's first sentence says "search" and "directory": it reads files.
Description, as the server wrote it Search the hand-curated Agent Toolbox directory by words and category. Matching is a case-insensitive substring over the name, description, and tags. It does not crawl the web or claim a server is healthy.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 untrusted-input.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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.
Looked at Nov 20, 2026, 19:06 UTC, unchanged since Oct 22, 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
- 3
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agenttoolbox.net/api/mcp: tools/list returned 4 tools to an anonymous client, including estimate_tokens (write), convert_schema (write), mcp_config (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnconvert_schema
The server marks "convert_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "convert_schema" says "convert": a word for a change.
- Warnmcp_config
The server marks "mcp_config" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.command), which can change anything it can reach.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:estimate_tokensChanges thingsdescription
Tools4 changed.~4 changedView diff
- Changed:convert_schemaChanges thingstitledescriptioninputSchemaannotations
- Changed:estimate_tokensChanges thingstitledescriptioninputSchemaannotations
- Changed:mcp_configChanges thingstitledescriptioninputSchemaannotations
- Changed:search_directoryOnly readstitledescriptioninputSchemaannotations
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agenttoolbox https://agenttoolbox.net/api/mcpclaude mcp add --transport http agenttoolbox https://agenttoolbox.net/api/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__agenttoolbox__search_directory"
],
"ask": [
"mcp__agenttoolbox__estimate_tokens",
"mcp__agenttoolbox__convert_schema",
"mcp__agenttoolbox__mcp_config"
],
"deny": []
}
}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 agenttoolbox. Review it before you use it.
Capability tags behind 2 rules
- mcp__agenttoolbox__mcp_config outbound
- mcp__agenttoolbox__search_directory private-data
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.johngee518/agenttoolbox/verify?hash=2d86e65f2eed7566e8e18aa8154e393f7f30d09f6efba724adec66f57f20f1e7" | jq -e '.changed == false'Pinned hash 2d86e65f2eed, from Nov 20, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.johngee518/agenttoolbox/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.johngee518/agenttoolbox)Source: MCP Registry. Synced Oct 21, 2026, 18:37 UTC.
Agent Toolbox MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Toolbox MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 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 Agent Toolbox MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Toolbox 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 Agent Toolbox MCP server have?
- 4 tools: 3 write, 1 read. estimate_tokens, convert_schema, mcp_config and search_directory.
Does the Agent Toolbox MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Toolbox MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): mcp_config.
Has the Agent Toolbox MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.