steamwebapi MCP server
io.github.sellrock-de/steamwebapisellrock-destreamable-httpv0.1.1Scanned
Live Steam Market API docs, schemas, products, games, markets and endpoint search.
11 tools: 1 change things and 10 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 steamwebapi MCP server can do
The steamwebapi MCP server is published by the GitHub account sellrock-de. It has 11 tools. It can create or change data (1 tool: call_readonly_endpoint), but cannot delete data. 10 tools only read.
1 tool reads private data (get_integration_skill); 2 tools bring in text other people can write (get_integration_skill and call_readonly_endpoint).
The fixed checks matched 3 findings (credentials-mention, base64-blob and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 0.1.1.
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.
11 tools
Changes things 1Claude Code: ask
call_readonly_endpointExecutes a documented steamwebapi GET endpoint with the caller API key from the MCP Authorization or X-Api-Key header.Reads text others write2 findings
Why it is in this group
- The name "call_readonly_endpoint" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.parameters.additionalProperties.anyOf[1].items.$ref contains a 51-character base64 string.
What this check looks forMatched text
inputSchema.properties.parameters.additionalProperties.anyOf[1].items.$ref: "#/properties/parameters/additionalProperties/anyOf/0"
- Warn
The server marks "call_readonly_endpoint" 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,"openWorldHint":true}; The name "call_readonly_endpoint" says "call": a word for a change.
Description, as the server wrote it Executes a documented steamwebapi GET endpoint with the caller API key from the MCP Authorization or X-Api-Key header. Refuses POST/PUT/PATCH/DELETE plus Proxy, Steam Guard and Tradeoffer endpoints.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
Only reads 10Show 10 read-only tools
get_conceptReturns a detailed explanation for a Steam / steamwebapi concept (identifiers, CS2 mechanics, pricing fields, inventory flags).No findings
Why it is in this group
- The name "get_concept" says "get": a word for reading.
Description, as the server wrote it Returns a detailed explanation for a Steam / steamwebapi concept (identifiers, CS2 mechanics, pricing fields, inventory flags). Built from curated domain knowledge specific to this platform.
get_endpointReturns the full OpenAPI operation object for a given path: parameters, request body, all response schemas, examples, and tags.No findings
Why it is in this group
- The name "get_endpoint" says "get": a word for reading.
Description, as the server wrote it Returns the full OpenAPI operation object for a given path: parameters, request body, all response schemas, examples, and tags. Use after search_endpoints to drill into a specific endpoint.
get_integration_skillRead the reusable SteamWebAPI SKILL.md for integration workflows, credentials, prices, item variants and CS2 release discovery.Reads private dataReads text others write1 finding
Why it is in this group
- The name "get_integration_skill" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "credential": it reads secrets.
- untrusted-inputThe description's first sentence says "read" and "web": it reads web pages, which anyone can write.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...API SKILL.md for integration workflows, credentials, prices, item variants and CS2 release..."
Description, as the server wrote it Read the reusable SteamWebAPI SKILL.md for integration workflows, credentials, prices, item variants and CS2 release discovery. Useful when the client does not expose MCP resources or initialization instructions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_pricingReturns public steamwebapi pricing plans, per-endpoint rate limits, API-key location, quota guidance and a recommended plan for the requested use case.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Returns public steamwebapi pricing plans, per-endpoint rate limits, API-key location, quota guidance and a recommended plan for the requested use case. Does not perform checkout or account actions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_conceptsLists every curated concept exposed by get_concept, optionally filtered by category.No findings
Why it is in this group
- The name "list_concepts" says "list": a word for reading.
Description, as the server wrote it Lists every curated concept exposed by get_concept, optionally filtered by category. Use to discover what domain explanations are available.
list_endpointsLists all steamwebapi.com endpoints (path + method + summary), optionally filtered by tag.No findings
Why it is in this group
- The name "list_endpoints" says "list": a word for reading.
Description, as the server wrote it Lists all steamwebapi.com endpoints (path + method + summary), optionally filtered by tag. Useful for quickly enumerating what is available.
list_gamesLists every game supported by steamwebapi.com with its slug, name, Steam appId, and the value to pass as `game=` in API queries.No findings
Why it is in this group
- The name "list_games" says "list": a word for reading.
Description, as the server wrote it Lists every game supported by steamwebapi.com with its slug, name, Steam appId, and the value to pass as `game=` in API queries.
list_marketsLists every third-party marketplace covered by the steamwebapi.com market price endpoints, with their domain and the games they cover.No findings
Why it is in this group
- The name "list_markets" says "list": a word for reading.
Description, as the server wrote it Lists every third-party marketplace covered by the steamwebapi.com market price endpoints, with their domain and the games they cover.
list_productsLists steamwebapi.com product packages (Price API, Inventory API, Float API, ...) with the endpoints each one bundles.No findings
Why it is in this group
- The name "list_products" says "list": a word for reading.
Description, as the server wrote it Lists steamwebapi.com product packages (Price API, Inventory API, Float API, ...) with the endpoints each one bundles. Use get_pricing for paid plans, request quotas and upgrade guidance.
search_endpointsFuzzy text search across all steamwebapi.com OpenAPI endpoints and Steam domain concepts (assetid, doppler phase, market_hash_name, etc.).No findings
Why it is in this group
- The name "search_endpoints" says "search": a word for reading.
Description, as the server wrote it Fuzzy text search across all steamwebapi.com OpenAPI endpoints and Steam domain concepts (assetid, doppler phase, market_hash_name, etc.). Returns ranked hits with path, method, tag and summary.
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 outbound.
- Reads private data1
- 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.
Looked at Nov 20, 2026, 19:10 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.steamwebapi.com/mcp: tools/list returned 11 tools to an anonymous client, including call_readonly_endpoint (write)
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.parameters.additionalProperties.anyOf[1].items.$ref contains a 51-character base64 string.
What this check looks forMatched text
inputSchema.properties.parameters.additionalProperties.anyOf[1].items.$ref: "#/properties/parameters/additionalProperties/anyOf/0"
The server marks "call_readonly_endpoint" 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,"openWorldHint":true}; The name "call_readonly_endpoint" says "call": a word for a change.
The description mentions "credentials".
What this check looks forMatched text
description: "...API SKILL.md for integration workflows, credentials, prices, item variants and CS2 release..."
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 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http steamwebapi https://mcp.steamwebapi.com/mcpclaude mcp add --transport http steamwebapi https://mcp.steamwebapi.com/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__steamwebapi__get_integration_skill",
"mcp__steamwebapi__search_endpoints",
"mcp__steamwebapi__get_endpoint",
"mcp__steamwebapi__list_endpoints",
"mcp__steamwebapi__list_games",
"mcp__steamwebapi__list_markets",
"mcp__steamwebapi__list_products",
"mcp__steamwebapi__get_concept",
"mcp__steamwebapi__list_concepts",
"mcp__steamwebapi__get_pricing"
],
"ask": [
"mcp__steamwebapi__call_readonly_endpoint"
],
"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 steamwebapi. Review it before you use it.
Capability tags behind 2 rules
- mcp__steamwebapi__get_integration_skill private-data, untrusted-input
- mcp__steamwebapi__call_readonly_endpoint 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.sellrock-de/steamwebapi/verify?hash=41433a843712607adc4ee25aa4a683e77b425c52a40dbf5a147eb1047fa5ce23" | jq -e '.changed == false'Pinned hash 41433a843712, from Nov 21, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.sellrock-de/steamwebapi/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.sellrock-de/steamwebapi)Source: MCP Registry. Synced Oct 21, 2026, 18:49 UTC.
steamwebapi MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the steamwebapi MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 1 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 steamwebapi MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the steamwebapi 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 steamwebapi MCP server have?
- 11 tools: 1 write, 10 read. call_readonly_endpoint, get_integration_skill, search_endpoints, get_endpoint, list_endpoints, list_games, list_markets, list_products and 3 more.
Does the steamwebapi MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the steamwebapi MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the steamwebapi MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.