Bike4Mind — the open-core AI workbench MCP server
com.bike4mind/bike4mindbike4mind.comstreamable-httpv1.3.0Scanned
Read-only facts on Bike4Mind: live model catalog, comparisons, open-core license, blog, updates.
9 tools: 2 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 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 Bike4Mind — the open-core AI workbench MCP server can do
The Bike4Mind — the open-core AI workbench MCP server is published by bike4mind.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (2 tools: get_open_core_facts and whats_new), but cannot delete data. 7 tools only read.
1 tool reads private data (get_comparison); 4 tools bring in text other people can write (get_comparison, search_blog_posts, get_blog_post and 1 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 12, 2026, version 1.3.0.
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.
9 tools
Changes things 2Claude Code: ask
get_open_core_factsThe open-core licensing and sovereignty facts: the BSL 1.1 → Apache-2.0 ratchet, the three-ring 'door out' (Usage Policy §0), and why the exit is the trust.1 finding
Why it is in this group
- The name "get_open_core_facts" says "get": a word for reading.
- The description's first verb is "open": 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 "get_open_core_facts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "get_open_core_facts" says "get": a word for reading.
Description, as the server wrote it The open-core licensing and sovereignty facts: the BSL 1.1 → Apache-2.0 ratchet, the three-ring 'door out' (Usage Policy §0), and why the exit is the trust.
Annotations the server declares
- readOnlyHint: true
whats_newDated product updates from Bike4Mind and its products (Paintbox, Tarot, Stocks and Vibes, Bedrock News, K2 Kanji, Manifold, Fleet, Overwatch, Bob), newest first.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 Dated product updates from Bike4Mind and its products (Paintbox, Tarot, Stocks and Vibes, Bedrock News, K2 Kanji, Manifold, Fleet, Overwatch, Bob), newest first. Each entry is one sentence with a kind (feature, art or fix), a product tag, and any screenshots or demo videos as absolute media URLs. Filter by product slug and/or a start date; omit both for the latest updates.
Annotations the server declares
- readOnlyHint: true
Only reads 7Show 7 read-only tools
get_blog_postFetch a bike4mind.com blog post's full content by slug.Reads text others writeNo findings
Why it is in this group
- The name "get_blog_post" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_blog_post" says "get" and "post": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "fetch" and "post": it reads posts, which other people can write.
Description, as the server wrote it Fetch a bike4mind.com blog post's full content by slug.
Annotations the server declares
- readOnlyHint: true
get_comparisonThe full Bike4Mind vs ChatGPT (OpenAI) vs Claude (Anthropic) vs Microsoft Copilot vs build-it-yourself comparison — the same table rendered at /compare, with the structural argumen…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_comparison" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it The full Bike4Mind vs ChatGPT (OpenAI) vs Claude (Anthropic) vs Microsoft Copilot vs build-it-yourself comparison — the same table rendered at /compare, with the structural argument: a lab can't be model-neutral, a cloud can't be cloud-neutral.
Annotations the server declares
- readOnlyHint: true
get_productOne product in the Bike4Mind ecosystem by slug: what it is, where Bike4Mind fits in it, status, category, links, and its latest dated updates.No findings
Why it is in this group
- The name "get_product" says "get": a word for reading.
Description, as the server wrote it One product in the Bike4Mind ecosystem by slug: what it is, where Bike4Mind fits in it, status, category, links, and its latest dated updates.
Annotations the server declares
- readOnlyHint: true
get_site_infoWhat Bike4Mind is, in machine-readable form: the open-core AI workbench (notebooks, agents, 13 artifact types, image gen, data lakes, MCP host+server), licensing (BSL 1.1 → Apache-…No findings
Why it is in this group
- The name "get_site_info" says "get": a word for reading.
Description, as the server wrote it What Bike4Mind is, in machine-readable form: the open-core AI workbench (notebooks, agents, 13 artifact types, image gen, data lakes, MCP host+server), licensing (BSL 1.1 → Apache-2.0 ratchet), deployment modes, and every agent-facing surface this site publishes.
Annotations the server declares
- readOnlyHint: true
list_modelsThe live Bike4Mind model catalog — synced from the live Bike4Mind models API (the same models the app offers).No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it The live Bike4Mind model catalog — synced from the live Bike4Mind models API (the same models the app offers). Filter by type ('text'|'image'), provider, or a substring query. Returns name, provider, context window, max output, cost tier (text models), and a per-entry source for auditing.
Annotations the server declares
- readOnlyHint: true
list_productsEvery product in the Bike4Mind ecosystem (Bike4Mind itself, Bedrock News, K2Kanji, Stocks and Vibes, Bob, 4XCiv, Paintbox, Overwatch, Tarot, Manifold, Fleet) plus Friends of Bike4M…Reads text others writeNo findings
Why it is in this group
- The name "list_products" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Every product in the Bike4Mind ecosystem (Bike4Mind itself, Bedrock News, K2Kanji, Stocks and Vibes, Bob, 4XCiv, Paintbox, Overwatch, Tarot, Manifold, Fleet) plus Friends of Bike4Mind, products other people built with it (tier 'friend', with a creator): name, one-line tagline, status (live, beta or in development), category, public URL where there is one, and the bike4mind.com page for each. Filter by category or status.
Annotations the server declares
- readOnlyHint: true
search_blog_postsSearch bike4mind.com blog posts.Reads text others writeNo findings
Why it is in this group
- The name "search_blog_posts" says "search": a word for reading.
What it can reach
- untrusted-inputThe name "search_blog_posts" says "search" and "post": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "search" and "post": it reads posts, which other people can write.
Description, as the server wrote it Search bike4mind.com blog posts. Multi-word queries are matched term by term across title, tags, summary and full body — so natural phrasing works ("open core licensing") and you do not have to guess a post's exact wording. Results are ranked: posts matching every term come first, partial matches follow rather than being discarded. Omit q to list the most recent posts. Returns compact listings with URLs.
Annotations the server declares
- 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- 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, 18:34 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://bike4mind.com/api/mcp: tools/list returned 9 tools to an anonymous client, including get_open_core_facts (write), whats_new (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "get_open_core_facts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "get_open_core_facts" says "get": a word for reading.
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 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http bike4mind https://bike4mind.com/api/mcpclaude mcp add --transport http bike4mind https://bike4mind.com/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__bike4mind__get_site_info",
"mcp__bike4mind__list_models",
"mcp__bike4mind__get_comparison",
"mcp__bike4mind__search_blog_posts",
"mcp__bike4mind__get_blog_post",
"mcp__bike4mind__list_products",
"mcp__bike4mind__get_product"
],
"ask": [
"mcp__bike4mind__get_open_core_facts",
"mcp__bike4mind__whats_new"
],
"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 bike4mind. Review it before you use it.
Capability tags behind 4 rules
- mcp__bike4mind__get_comparison private-data, untrusted-input
- mcp__bike4mind__search_blog_posts untrusted-input
- mcp__bike4mind__get_blog_post untrusted-input
- mcp__bike4mind__list_products 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/com.bike4mind/bike4mind/verify?hash=6d5fb0d22f95e503e4cc4ec969a2c30081a83666559e59c43c638f72cacaca63" | jq -e '.changed == false'Pinned hash 6d5fb0d22f95, from Nov 12, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.bike4mind/bike4mind/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.bike4mind/bike4mind)Source: MCP Registry. Synced Oct 21, 2026, 17:51 UTC.
Bike4Mind — the open-core AI workbench MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Bike4Mind — the open-core AI workbench MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Bike4Mind — the open-core AI workbench MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Bike4Mind — the open-core AI workbench 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 Bike4Mind — the open-core AI workbench MCP server have?
- 9 tools: 2 write, 7 read. get_open_core_facts, whats_new, get_site_info, list_models, get_comparison, search_blog_posts, get_blog_post, list_products and 1 more.
Does the Bike4Mind — the open-core AI workbench MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Bike4Mind — the open-core AI workbench MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Bike4Mind — the open-core AI workbench MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.