ToolSchema Forge MCP server
dev.workers.toolschemaforge.toolschema-forge/toolschema-forgetoolschema-forge.toolschemaforge.workers.devstreamable-httpv1.1.0Scanned
Convert, lint and generate LLM tool schemas for OpenAI, Anthropic, Gemini and MCP
5 tools: 5 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 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 ToolSchema Forge MCP server can do
The ToolSchema Forge MCP server is published by toolschema-forge.toolschemaforge.workers.dev, a domain the MCP Registry verified. It has 5 tools. It can create or change data (5 tools: convert_tool_schema, lint_tool_schema, openapi_to_tools, batch_convert_tool_schemas and 1 more), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 1.1.0.
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.
5 tools
Changes things 5Claude Code: ask
batch_convert_tool_schemasConvert up to 50 tool definitions at once to the chosen formats, with per-tool issues and ready-to-use bundles.1 finding
Why it is in this group
- The name "batch_convert_tool_schemas" 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 "batch_convert_tool_schemas" 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 "batch_convert_tool_schemas" says "convert": a word for a change.
Description, as the server wrote it Convert up to 50 tool definitions at once to the chosen formats, with per-tool issues and ready-to-use bundles. Free: 5 calls/hour per IP with arguments up to 8 KB; then $0.05 USDC per call via x402.
Annotations the server declares
- title: Batch convert tool schemas
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
convert_tool_schemaConvert one LLM tool/function definition between OpenAI, OpenAI strict mode, Anthropic, Gemini, MCP and plain JSON Schema.1 finding
Why it is in this group
- The name "convert_tool_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_tool_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_tool_schema" says "convert": a word for a change.
Description, as the server wrote it Convert one LLM tool/function definition between OpenAI, OpenAI strict mode, Anthropic, Gemini, MCP and plain JSON Schema. The input format is auto-detected. Every change is reported as an issue with a JSON pointer. Free: 5 calls/hour per IP with arguments up to 8 KB; then $0.01 USDC per call via x402.
Annotations the server declares
- title: Convert tool schema
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lint_tool_schemaCheck one LLM tool definition against each provider's schema rules (OpenAI strict, Anthropic, Gemini, MCP) and report errors and warnings with fixes.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 one LLM tool definition against each provider's schema rules (OpenAI strict, Anthropic, Gemini, MCP) and report errors and warnings with fixes. Free: 5 calls/hour per IP with arguments up to 8 KB; then $0.005 USDC per call via x402.
Annotations the server declares
- title: Lint tool schema
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mcp_manifestGenerate an MCP server manifest (tools with inputSchema, titles, annotations, HTTP bindings) and a TypeScript stdio server stub from an OpenAPI spec or a list of tools.1 finding
Why it is in this group
- The description's first verb is "generate": 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 "mcp_manifest" 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 description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate an MCP server manifest (tools with inputSchema, titles, annotations, HTTP bindings) and a TypeScript stdio server stub from an OpenAPI spec or a list of tools. Free: 5 calls/hour per IP with arguments up to 8 KB; then $0.15 USDC per call via x402.
Annotations the server declares
- title: MCP manifest + server stub
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
openapi_to_toolsTurn an OpenAPI 3.x or Swagger 2.0 spec (JSON object) into LLM tool definitions in the chosen format, one tool per operation.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 Turn an OpenAPI 3.x or Swagger 2.0 spec (JSON object) into LLM tool definitions in the chosen format, one tool per operation. Free: 5 calls/hour per IP with arguments up to 8 KB; then $0.02 USDC per call via x402.
Annotations the server declares
- title: OpenAPI to tools
- 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 private-data or untrusted-input or outbound.
- Reads private data0
- 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 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.
Looked at Nov 16, 2026, 14:23 UTC, unchanged since Oct 25, 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://toolschema-forge.toolschemaforge.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including convert_tool_schema (write), lint_tool_schema (write), openapi_to_tools (write), batch_convert_tool_schemas (write), mcp_manifest (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "convert_tool_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_tool_schema" says "convert": a word for a change.
The server marks "batch_convert_tool_schemas" 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 "batch_convert_tool_schemas" says "convert": a word for a change.
- Warnmcp_manifest
The server marks "mcp_manifest" 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 description's first verb is "generate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http toolschema-forge https://toolschema-forge.toolschemaforge.workers.dev/mcpclaude mcp add --transport http toolschema-forge https://toolschema-forge.toolschemaforge.workers.dev/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": [],
"ask": [
"mcp__toolschema-forge__convert_tool_schema",
"mcp__toolschema-forge__lint_tool_schema",
"mcp__toolschema-forge__openapi_to_tools",
"mcp__toolschema-forge__batch_convert_tool_schemas",
"mcp__toolschema-forge__mcp_manifest"
],
"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 toolschema-forge. Review it before you use it.
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/dev.workers.toolschemaforge.toolschema-forge/toolschema-forge/verify?hash=5eb8c17b08c0934f18f9bb09efe2b08bd2d30a1ad64f11756f385e0a91e52b4b" | jq -e '.changed == false'Pinned hash 5eb8c17b08c0, from Nov 9, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.toolschemaforge.toolschema-forge/toolschema-forge/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.toolschemaforge.toolschema-forge/toolschema-forge)Source: MCP Registry. Synced Oct 24, 2026, 20:20 UTC.
ToolSchema Forge MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ToolSchema Forge MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 5 of which can change, send or delete something, and 3 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 ToolSchema Forge MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ToolSchema Forge 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 ToolSchema Forge MCP server have?
- 5 tools: 5 write. convert_tool_schema, lint_tool_schema, openapi_to_tools, batch_convert_tool_schemas and mcp_manifest.
Does the ToolSchema Forge MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ToolSchema Forge MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ToolSchema Forge MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.