Connect Alkemata Knowledge Gateway and your agent gets 32 tools, among them add_map_content, alkemata-get-notebook-text, alkemata-get-published-content. It answers at https://alkemata.com/wp-json/mcp/alkemata-public over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 3 of 4 times since 28 September 2026; the last check, on 14 November 2026, succeeded.
Search and retrieve published Alkemata articles, pages, and guidance through a read-only MCP server.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_map_content | Add a topic near its named parent category; omit category_name for a top-level topic. Inputs: title, summary, content, category_name, map_id, language |
alkemata-get-notebook-text | Read published notebook text and source code, paging with next_offset; returns preview and .ipynb URLs. Inputs: notebook_id, offset, limit |
alkemata-get-published-content | Read a published WordPress post or page through the existing public MCP. Inputs: post_id |
alkemata-search-notebooks | Search published notebook titles, filenames, markdown, code and text outputs by keyword. Inputs: query, limit |
alkemata-search-published-content | Search published WordPress posts or pages through the existing public MCP. Inputs: query, post_type, per_page |
create_topic_at_position | Create a topic at exact coordinates; omit map_id when there is one map. Prefer add_map_content for automatic placement. Inputs: title, summary, content, x, y, map_id |
edit_topic | Edit an existing published topic. Read it with get_topic first and pass its version as expected_revision. Omitted fields are preserved; content replaces all content blocks. Inputs: topic_id, expected_revision, title, summary, content, language |
find_related_map_topics | Find similar published map posts and return their text, IDs, category and position for study planning. Inputs: title, summary, draft_text, map_id, limit |
get_agent_guidance | Start here for article and map reading, anonymous proposals, and authenticated map creation rules. |
get_app_info | Start here for the canonical endpoint, map ID, and the difference between pending proposals and map publishing. |
get_region | Return published objects for a viewport; obtain map_id from list_maps first. Inputs: map_id, min_x, min_y, max_x, max_y, zoom |
get_topic | Return complete permitted blocks, published sources and relationships for one topic. Inputs: topic_id, revision_id |
get_trail | Return a published learning trail with steps and branches. Inputs: trail_id |
list_map_categories | List published topic/category names and depth on a map for add_map_content. Inputs: map_id |
list_maps | List exact map IDs and world bounds before creating content. |
notebooks_upload_file | Publish an attached .ipynb file and return its public preview link in url and preview_url. Inputs: file |
notebooks_upload_json | Publish notebook JSON as a .ipynb file and return its public preview link in url and preview_url. Inputs: notebook, filename |
openproject_create_wiki_page | Create a page in a wiki where the signed-in user has edit permission. Inputs: project_id, title, text |
openproject_create_work_package | Create a work package in a project where the signed-in user may add work packages. Inputs: project_id, type_id, subject, description |
openproject_get_wiki_page | Read a wiki page's text and lock_version before editing it. Inputs: id |
openproject_get_work_package | Read a work package, including its lock_version for a later edit. Inputs: id |
openproject_list_projects | Start here to find project IDs, enabled wiki access, and work package type IDs. |
openproject_list_wiki_pages | List up to 100 wiki pages in a project where the signed-in user may view its wiki. Inputs: project_id |
openproject_list_work_packages | List up to 50 recent work packages in a permitted project, optionally filtering subjects. Inputs: project_id, query |
openproject_update_wiki_page | Replace wiki page text only when the supplied lock_version is still current. Inputs: id, lock_version, text |
openproject_update_work_package | Edit subject, description, or status after reading the current lock_version. Inputs: id, lock_version, subject, description, status_id |
openproject_upload_file | Upload a user-attached ChatGPT file as a project document or attach it to an existing work package or wiki page. Inputs: file, project_id, target_type, target_id, title, description |
propose_project | Submit a project idea for editorial review; this never creates a public post or task. Inputs: title, problem, proposed_experiment, related_targets, expected_value, client_submission_id |
publish_study_path | Atomically add a study text, related links and ordered learning trail near similar map posts. First call find_related_map_topics. Put selected existing topic IDs in learning order; the new post is appended as the last trail step. The server Inputs: title, summary, content, related_topics, idempotency_key, map_id |
search_topics | Search published topic titles and summaries. Responses are bounded to 100. Inputs: query, language, limit |
submit_feedback | Submit private feedback for editorial review. Provide one published article or topic; this never publishes content. Inputs: category, text, article_id, topic_id, source_url, display_name |
suggest_connection | Suggest a connection between two published targets for review; this never creates a map edge. Inputs: from, to, relation, rationale, source_urls, client_submission_id |
Every block below points at https://alkemata.com/wp-json/mcp/alkemata-public. Pick your client and copy.
claude mcp add --transport http alkemata-knowledge-gateway https://alkemata.com/wp-json/mcp/alkemata-public
{
"mcpServers": {
"alkemata-knowledge-gateway": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://alkemata.com/wp-json/mcp/alkemata-public"]
}
}
}{
"mcpServers": {
"alkemata-knowledge-gateway": {
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"servers": {
"alkemata-knowledge-gateway": {
"type": "http",
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"context_servers": {
"alkemata-knowledge-gateway": {
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"mcpServers": {
"alkemata-knowledge-gateway": {
"serverUrl": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"mcpServers": {
"alkemata-knowledge-gateway": {
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}name: Alkemata Knowledge Gateway
version: 0.0.1
schema: v1
mcpServers:
- name: Alkemata Knowledge Gateway
type: streamable-http
url: https://alkemata.com/wp-json/mcp/alkemata-public{
"mcpServers": {
"alkemata-knowledge-gateway": {
"httpUrl": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"mcpServers": {
"alkemata-knowledge-gateway": {
"type": "http",
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}{
"mcpServers": {
"alkemata-knowledge-gateway": {
"url": "https://alkemata.com/wp-json/mcp/alkemata-public"
}
}
}goose://extension?url=https%3A%2F%2Falkemata.com%2Fwp-json%2Fmcp%2Falkemata-public&type=streamable_http&id=alkemata-knowledge-gateway&name=Alkemata%20Knowledge%20Gateway
It answered our last check on 14 November 2026 in 79 ms. Over 4 checks since 28 September 2026 it answered 3. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by alkemata.com and served from alkemata.com, the vendor's own domain: https://alkemata.com/wp-json/mcp/alkemata-public.
32, as returned by the server's own tools/list on 17 November 2026: add_map_content, alkemata-get-notebook-text, alkemata-get-published-content, alkemata-search-notebooks, alkemata-search-published-content, create_topic_at_position, edit_topic, find_related_map_topics, and 24 more.
It answered our last check on 14 November 2026 in 79 ms. Over 4 checks since 28 September 2026 it answered 3.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://alkemata.com/wp-json/mcp/alkemata-public. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.alkemata. Endpoint host: alkemata.com. ARD identifier: urn:air:com.alkemata:mcp:public-knowledge.
First indexed 28 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.