← DeepnoteCONTENT HISTORY

Update to Deepnote

Snapshot Nov 14, 2026 · 00:15 UTC · version 3.0.0

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for deepnote-links

Full description — Now says: MCP

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Deepnote and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 22:52 UTC

Deepnote app

After

Nov 14, 2026 · 00:15 UTC

MCP

Skill instructions

Before

Sep 30, 2026 · 22:52 UTC

Deepnote app project, notebook, or workspace data. Use this skill to build user-facing Deepnote web links from Deepnote app tool data. Prefer links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses instead of ...

After

Nov 14, 2026 · 00:15 UTC

MCP project, notebook, or workspace data. Use this skill to build user-facing Deepnote web links from MCP data. Prefer `generate_project_url`, then links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses. Ever...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,31 +1,32 @@
 ---
 name: deepnote-links
-description: Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from Deepnote app project, notebook, or workspace data.
+description: Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from MCP project, notebook, or workspace data.
 ---
 
 # Deepnote Links
 
-Use this skill to build user-facing Deepnote web links from Deepnote app tool data. Prefer links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses instead of guessing from names alone. Every project and notebook link built from Deepnote app data must include the UTM parameters below.
+Use this skill to build user-facing Deepnote web links from MCP data. Prefer `generate_project_url`, then links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses. Every project and notebook link must include the UTM parameters below.
+
+## Server-Generated Links
+
+Use `generate_project_url` as the preferred source for a single project or notebook URL, then append the UTM parameters below. Fall back to the manual URL shapes when the tool is unavailable, when building many links from one `list_projects` or `search` response, or when a workspace link is needed.
+
+Do not retry `Project not found` or `Notebook not found` errors with guessed IDs. When both IDs are supplied, the notebook must belong to the project.
 
 ## Inputs To Resolve
 
-1. Call `get_me` when workspace-aware links are useful. Use `workspace.id` and `workspace.slug`; do not use OAuth tokens, user email, or other auth details in links or summaries.
-2. Resolve the project with `list_projects` or `search`. Use the project `id`, `name`, and `slug` if the app response exposes one.
+1. Call `get_me` when workspace-aware links are useful. Use `workspace.id` and `workspace.slug`; do not use the API key name, bearer token, or user email in links or summaries.
+2. Resolve the project with `list_projects` or `search`. Use the project `id`, `name`, and `slug` if the MCP response exposes one.
 3. Resolve notebook links with `get_notebook` when possible. Use the notebook `id`, `name`, and parent project data.
 4. If the exact project or notebook is ambiguous, ask a short clarification or provide a compact candidate list with links only for unambiguous matches.
 
-## Creation Link Rules
+## Links After Creation
 
-When linking after a creation workflow, use the resource IDs returned by the write tools as the source of truth:
-
-- If `create_notebook` returned a notebook, build the notebook link for that returned notebook ID. Do not substitute the first notebook on the project or the default notebook created by `create_project`.
-- If `create_project` created a project and no separate `create_notebook` call was made, use the default notebook created with the project only when a notebook link is needed for that active notebook.
-- If both the project default notebook and a later `create_notebook` result are present, the later `create_notebook` result is the notebook to link unless the user explicitly asks for the default notebook.
-- If parent project data is missing for the created notebook, call `get_notebook` for the target notebook ID or use the known project ID from the creation workflow before constructing the link.
+Link the active notebook as defined by the Active Notebook Rule in `deepnote-notebooks`: the notebook returned by `create_notebook` when one was called, otherwise the default notebook of the project returned by `create_project`. If parent project data is missing for that notebook, call `get_notebook` for its ID or use the project ID from the creation workflow before building the link.
 
 ## URL Shapes
 
-Use the production web origin `https://deepnote.com` for Deepnote app links. Do not derive the web origin from API or tool hosts.
+Use the production web origin `https://deepnote.com` for Deepnote MCP links. Do not derive the web origin from API or MCP hosts.
 
 Prefer workspace-scoped links when `get_me` returns both `workspace.slug` and `workspace.id`:
 
@@ -47,7 +48,7 @@
 
 Use the most canonical segment available:
 
-1. If the app response exposes a `slug`, use it.
+1. If the MCP response exposes a `slug`, use it.
 2. Otherwise, for simple names, build a readable segment as `{slugifiedName}-{id}`.
 3. If exact slugification is uncertain, the name is missing, or the name has unusual characters, use the ID alone.
 
@@ -66,40 +67,34 @@
 ## Optional Suffixes
 
 - File paths, when exposed and requested, append after the project segment as `/{encodeURIComponent(filePath)}`.
-- Cell or block anchors append as `#anchor`.
-- Only generate published app links such as `/app/{authorSlug}/{projectSegment}` or `/streamlit-apps/{streamlitAppId}` when Deepnote app data explicitly exposes the published author slug or Streamlit app ID.
+- Cell or block anchors append after the UTM query string as `#anchor`.
+- Use Streamlit URLs returned by `create_streamlit_app` or `list_streamlit_apps`; do not assemble them from an app ID.
+- Use the data app URL from `dataApp.url` in `get_project`; never construct it.
 
 ## UTM Parameters
 
-For every project and notebook link built from Deepnote app data, add OpenAI attribution query parameters:
+Every project and notebook link gets these parameters. `utm_source` and `utm_campaign` depend on the host:
+
+| Host | `utm_source` | `utm_campaign` |
+| --- | --- | --- |
+| Codex | `codex` | `openaimcp` |
+| Claude Code | `claude-code` | `claudemcp` |
+| Claude Desktop or Cowork | `claude-desktop` | `claudemcp` |
 
 ```text
-https://deepnote.com/<path>?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content={notebook_id}&utm_term={tool_name}
+https://deepnote.com/<path>?utm_source={host_source}&utm_medium=mcp&utm_campaign={host_campaign}&utm_content={id}&utm_term={tool_name}
 ```
 
-Use these values exactly; braces mark placeholders and are not part of the final URL:
-
-- `utm_source=openai`
-- `utm_medium=mcp`
-- `utm_campaign=openaimcp`
-- `utm_content={notebook_id}`
-- `utm_term={tool_name}`
-
-For notebook links, set `utm_content` to the notebook ID. For project-only links, set `utm_content` to the project ID; when a project link represents a specific notebook's parent project, use that notebook ID instead.
-
-Set `utm_term` to the Deepnote app tool or workflow that produced or grounded the link, such as `list_projects`, `search`, `get_notebook`, or `workspace_summary`. Use lowercase snake_case values and URL-encode if needed.
-
-For links to newly created notebooks, set `utm_content` to the created notebook ID and prefer `utm_term=create_notebook`; use `utm_term=get_notebook` when a follow-up `get_notebook` call provided the fields needed to construct the link.
-
-Add UTM parameters before any URL fragment. Use `?` when the URL has no existing query string, otherwise use `&`. Preserve non-UTM query parameters if they already exist, and replace any existing `utm_source`, `utm_medium`, `utm_campaign`, `utm_content`, or `utm_term` values instead of duplicating them.
+- `utm_content` is the notebook ID for notebook links and the project ID for project links.
+- `utm_term` is the tool that produced the link, such as `generate_project_url`, `list_projects`, `search`, `get_notebook`, or `create_notebook`, or `workspace_summary` for links built by the workspace summary.
 
 ## Response Style
 
-Return Markdown links with human-readable labels:
+Return Markdown links with human-readable labels. Shown here with Codex values; in Claude Code use `utm_source=claude-code&utm_campaign=claudemcp` instead:
 
 ```markdown
-[Project Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content=project-id&utm_term=list_projects)
-[Notebook Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id/notebook/notebook-id?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content=notebook-id&utm_term=get_notebook)
+[Project Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=project-id&utm_term=generate_project_url)
+[Notebook Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id/notebook/notebook-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=notebook-id&utm_term=generate_project_url)
 ```
 
 For lists, inventories, and workspace summaries, put links in the `Project` or `Notebook` column and keep IDs in a separate column only when they help disambiguate. When a table has a `Notebook` column, hyperlink the notebook name itself. If a link cannot be built safely because workspace, project, or notebook data is missing, say which field is missing and how to resolve it.
Full technical diff · 2 changed fields

changed /description

BEFORE
"Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from Deepnote app project, notebook, or workspace data."
AFTER
"Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from MCP project, notebook, or workspace data."

changed /skill_md_contents

BEFORE
"---\nname: deepnote-links\ndescription: Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from Deepnote app project, notebook, or workspace data.\n---\n\n# Deepnote Links\n\nUse this skill to build user-facing Deepnote web links from Deepnote app tool data. Prefer links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses instead of guessing from names alone. Every project and notebook link built from Deepnote app data must include the UTM parameters below.\n\n## Inputs To Resolve\n\n1. Call `get_me` when workspace-aware links are useful. Use `workspace.id` and `workspace.slug`; do not use OAuth tokens, user email, or other auth details in links or summaries.\n2. Resolve the project with `list_projects` or `search`. Use the project `id`, `name`, and `slug` if the app response exposes one.\n3. Resolve notebook links with `get_notebook` when possible. Use the notebook `id`, `name`, and parent project data.\n4. If the exact project or notebook is ambiguous, ask a short clarification or provide a compact candidate list with links only for unambiguous matches.\n\n## Creation Link Rules\n\nWhen linking after a creation workflow, use the resource IDs returned by the write tools as the source of truth:\n\n- If `create_notebook` returned a notebook, build the notebook link for that returned notebook ID. Do not substitute the first notebook on the project or the default notebook created by `create_project`.\n- If `create_project` created a project and no separate `create_notebook` call was made, use the default notebook created with the project only when a notebook link is needed for that active notebook.\n- If both the project default notebook and a later `create_notebook` result are present, the later `create_notebook` result is the notebook to link unless the user explicitly asks for the default notebook.\n- If parent project data is missing for the created notebook, call `get_notebook` for the target notebook ID or use the known project ID from the creation workflow before constructing the link.\n\n## URL Shapes\n\nUse the production web origin `https://deepnote.com` for Deepnote app links. Do not derive the web origin from API or tool hosts.\n\nPrefer workspace-scoped links when `get_me` returns both `workspace.slug` and `workspace.id`:\n\n```text\nworkspaceSlugWithId = {workspace.slug}-{workspace.id}\nworkspace link = {origin}/workspace/{workspaceSlugWithId}\nproject link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}\nnotebook link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\nIf workspace data is not available, use the non-workspace project route:\n\n```text\nproject link = {origin}/project/{projectSegment}\nnotebook link = {origin}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\n## Slug Segments\n\nUse the most canonical segment available:\n\n1. If the app response exposes a `slug`, use it.\n2. Otherwise, for simple names, build a readable segment as `{slugifiedName}-{id}`.\n3. If exact slugification is uncertain, the name is missing, or the name has unusual characters, use the ID alone.\n\nDeepnote project routing accepts UUID-only project segments, so `{project.id}` is the safest fallback. Notebook routing uses ID-only segments when a notebook name is not available, so `{notebook.id}` is the safest notebook fallback.\n\nDeepnote's readable slugs are created with strict slugification: spaces become hyphens, `/` becomes `-`, unsafe characters are stripped or normalized, and case is preserved. Examples:\n\n```text\nSubject Tracker + 0508fc64-b2c8-4982-b6a0-2590c94b6000\n=> Subject-Tracker-0508fc64-b2c8-4982-b6a0-2590c94b6000\n\nfolder/notebook 10% + a1b2c3d4\n=> folder-notebook-10percent-a1b2c3d4\n```\n\n## Optional Suffixes\n\n- File paths, when exposed and requested, append after the project segment as `/{encodeURIComponent(filePath)}`.\n- Cell or block anchors append as `#anchor`.\n- Only generate published app links such as `/app/{authorSlug}/{projectSegment}` or `/streamlit-apps/{streamlitAppId}` when Deepnote app data explicitly exposes the published author slug or Streamlit app ID.\n\n## UTM Parameters\n\nFor every project and notebook link built from Deepnote app data, add OpenAI attribution query parameters:\n\n```text\nhttps://deepnote.com/<path>?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content={notebook_id}&utm_term={tool_name}\n```\n\nUse these values exactly; braces mark placeholders and are not part of the final URL:\n\n- `utm_source=openai`\n- `utm_medium=mcp`\n- `utm_campaign=openaimcp`\n- `utm_content={notebook_id}`\n- `utm_term={tool_name}`\n\nFor notebook links, set `utm_content` to the notebook ID. For project-only links, set `utm_content` to the project ID; when a project link represents a specific notebook's parent project, use that notebook ID instead.\n\nSet `utm_term` to the Deepnote app tool or workflow that produced or grounded the link, such as `list_projects`, `search`, `get_notebook`, or `workspace_summary`. Use lowercase snake_case values and URL-encode if needed.\n\nFor links to newly created notebooks, set `utm_content` to the created notebook ID and prefer `utm_term=create_notebook`; use `utm_term=get_notebook` when a follow-up `get_notebook` call provided the fields needed to construct the link.\n\nAdd UTM parameters before any URL fragment. Use `?` when the URL has no existing query string, otherwise use `&`. Preserve non-UTM query parameters if they already exist, and replace any existing `utm_source`, `utm_medium`, `utm_campaign`, `utm_content`, or `utm_term` values instead of duplicating them.\n\n## Response Style\n\nReturn Markdown links with human-readable labels:\n\n```markdown\n[Project Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content=project-id&utm_term=list_projects)\n[Notebook Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id/notebook/notebook-id?utm_source=openai&utm_medium=mcp&utm_campaign=openaimcp&utm_content=notebook-id&utm_term=get_notebook)\n```\n\nFor lists, inventories, and workspace summaries, put links in the `Project` or `Notebook` column and keep IDs in a separate column only when they help disambiguate. When a table has a `Notebook` column, hyperlink the notebook name itself. If a link cannot be built safely because workspace, project, or notebook data is missing, say which field is missing and how to resolve it.\n"
AFTER
"---\nname: deepnote-links\ndescription: Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from MCP project, notebook, or workspace data.\n---\n\n# Deepnote Links\n\nUse this skill to build user-facing Deepnote web links from MCP data. Prefer `generate_project_url`, then links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses. Every project and notebook link must include the UTM parameters below.\n\n## Server-Generated Links\n\nUse `generate_project_url` as the preferred source for a single project or notebook URL, then append the UTM parameters below. Fall back to the manual URL shapes when the tool is unavailable, when building many links from one `list_projects` or `search` response, or when a workspace link is needed.\n\nDo not retry `Project not found` or `Notebook not found` errors with guessed IDs. When both IDs are supplied, the notebook must belong to the project.\n\n## Inputs To Resolve\n\n1. Call `get_me` when workspace-aware links are useful. Use `workspace.id` and `workspace.slug`; do not use the API key name, bearer token, or user email in links or summaries.\n2. Resolve the project with `list_projects` or `search`. Use the project `id`, `name`, and `slug` if the MCP response exposes one.\n3. Resolve notebook links with `get_notebook` when possible. Use the notebook `id`, `name`, and parent project data.\n4. If the exact project or notebook is ambiguous, ask a short clarification or provide a compact candidate list with links only for unambiguous matches.\n\n## Links After Creation\n\nLink the active notebook as defined by the Active Notebook Rule in `deepnote-notebooks`: the notebook returned by `create_notebook` when one was called, otherwise the default notebook of the project returned by `create_project`. If parent project data is missing for that notebook, call `get_notebook` for its ID or use the project ID from the creation workflow before building the link.\n\n## URL Shapes\n\nUse the production web origin `https://deepnote.com` for Deepnote MCP links. Do not derive the web origin from API or MCP hosts.\n\nPrefer workspace-scoped links when `get_me` returns both `workspace.slug` and `workspace.id`:\n\n```text\nworkspaceSlugWithId = {workspace.slug}-{workspace.id}\nworkspace link = {origin}/workspace/{workspaceSlugWithId}\nproject link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}\nnotebook link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\nIf workspace data is not available, use the non-workspace project route:\n\n```text\nproject link = {origin}/project/{projectSegment}\nnotebook link = {origin}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\n## Slug Segments\n\nUse the most canonical segment available:\n\n1. If the MCP response exposes a `slug`, use it.\n2. Otherwise, for simple names, build a readable segment as `{slugifiedName}-{id}`.\n3. If exact slugification is uncertain, the name is missing, or the name has unusual characters, use the ID alone.\n\nDeepnote project routing accepts UUID-only project segments, so `{project.id}` is the safest fallback. Notebook routing uses ID-only segments when a notebook name is not available, so `{notebook.id}` is the safest notebook fallback.\n\nDeepnote's readable slugs are created with strict slugification: spaces become hyphens, `/` becomes `-`, unsafe characters are stripped or normalized, and case is preserved. Examples:\n\n```text\nSubject Tracker + 0508fc64-b2c8-4982-b6a0-2590c94b6000\n=> Subject-Tracker-0508fc64-b2c8-4982-b6a0-2590c94b6000\n\nfolder/notebook 10% + a1b2c3d4\n=> folder-notebook-10percent-a1b2c3d4\n```\n\n## Optional Suffixes\n\n- File paths, when exposed and requested, append after the project segment as `/{encodeURIComponent(filePath)}`.\n- Cell or block anchors append after the UTM query string as `#anchor`.\n- Use Streamlit URLs returned by `create_streamlit_app` or `list_streamlit_apps`; do not assemble them from an app ID.\n- Use the data app URL from `dataApp.url` in `get_project`; never construct it.\n\n## UTM Parameters\n\nEvery project and notebook link gets these parameters. `utm_source` and `utm_campaign` depend on the host:\n\n| Host | `utm_source` | `utm_campaign` |\n| --- | --- | --- |\n| Codex | `codex` | `openaimcp` |\n| Claude Code | `claude-code` | `claudemcp` |\n| Claude Desktop or Cowork | `claude-desktop` | `claudemcp` |\n\n```text\nhttps://deepnote.com/<path>?utm_source={host_source}&utm_medium=mcp&utm_campaign={host_campaign}&utm_content={id}&utm_term={tool_name}\n```\n\n- `utm_content` is the notebook ID for notebook links and the project ID for project links.\n- `utm_term` is the tool that produced the link, such as `generate_project_url`, `list_projects`, `search`, `get_notebook`, or `create_notebook`, or `workspace_summary` for links built by the workspace summary.\n\n## Response Style\n\nReturn Markdown links with human-readable labels. Shown here with Codex values; in Claude Code use `utm_source=claude-code&utm_campaign=claudemcp` instead:\n\n```markdown\n[Project Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=project-id&utm_term=generate_project_url)\n[Notebook Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id/notebook/notebook-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=notebook-id&utm_term=generate_project_url)\n```\n\nFor lists, inventories, and workspace summaries, put links in the `Project` or `Notebook` column and keep IDs in a separate column only when they help disambiguate. When a table has a `Notebook` column, hyperlink the notebook name itself. If a link cannot be built safely because workspace, project, or notebook data is missing, say which field is missing and how to resolve it.\n"
Full snapshot data
{
  "description": "Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from MCP project, notebook, or workspace data.",
  "included_files": [],
  "name": "deepnote-links",
  "skill_md_contents": "---\nname: deepnote-links\ndescription: Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from MCP project, notebook, or workspace data.\n---\n\n# Deepnote Links\n\nUse this skill to build user-facing Deepnote web links from MCP data. Prefer `generate_project_url`, then links grounded in `get_me`, `list_projects`, `search`, and `get_notebook` responses. Every project and notebook link must include the UTM parameters below.\n\n## Server-Generated Links\n\nUse `generate_project_url` as the preferred source for a single project or notebook URL, then append the UTM parameters below. Fall back to the manual URL shapes when the tool is unavailable, when building many links from one `list_projects` or `search` response, or when a workspace link is needed.\n\nDo not retry `Project not found` or `Notebook not found` errors with guessed IDs. When both IDs are supplied, the notebook must belong to the project.\n\n## Inputs To Resolve\n\n1. Call `get_me` when workspace-aware links are useful. Use `workspace.id` and `workspace.slug`; do not use the API key name, bearer token, or user email in links or summaries.\n2. Resolve the project with `list_projects` or `search`. Use the project `id`, `name`, and `slug` if the MCP response exposes one.\n3. Resolve notebook links with `get_notebook` when possible. Use the notebook `id`, `name`, and parent project data.\n4. If the exact project or notebook is ambiguous, ask a short clarification or provide a compact candidate list with links only for unambiguous matches.\n\n## Links After Creation\n\nLink the active notebook as defined by the Active Notebook Rule in `deepnote-notebooks`: the notebook returned by `create_notebook` when one was called, otherwise the default notebook of the project returned by `create_project`. If parent project data is missing for that notebook, call `get_notebook` for its ID or use the project ID from the creation workflow before building the link.\n\n## URL Shapes\n\nUse the production web origin `https://deepnote.com` for Deepnote MCP links. Do not derive the web origin from API or MCP hosts.\n\nPrefer workspace-scoped links when `get_me` returns both `workspace.slug` and `workspace.id`:\n\n```text\nworkspaceSlugWithId = {workspace.slug}-{workspace.id}\nworkspace link = {origin}/workspace/{workspaceSlugWithId}\nproject link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}\nnotebook link = {origin}/workspace/{workspaceSlugWithId}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\nIf workspace data is not available, use the non-workspace project route:\n\n```text\nproject link = {origin}/project/{projectSegment}\nnotebook link = {origin}/project/{projectSegment}/notebook/{notebookSegment}\n```\n\n## Slug Segments\n\nUse the most canonical segment available:\n\n1. If the MCP response exposes a `slug`, use it.\n2. Otherwise, for simple names, build a readable segment as `{slugifiedName}-{id}`.\n3. If exact slugification is uncertain, the name is missing, or the name has unusual characters, use the ID alone.\n\nDeepnote project routing accepts UUID-only project segments, so `{project.id}` is the safest fallback. Notebook routing uses ID-only segments when a notebook name is not available, so `{notebook.id}` is the safest notebook fallback.\n\nDeepnote's readable slugs are created with strict slugification: spaces become hyphens, `/` becomes `-`, unsafe characters are stripped or normalized, and case is preserved. Examples:\n\n```text\nSubject Tracker + 0508fc64-b2c8-4982-b6a0-2590c94b6000\n=> Subject-Tracker-0508fc64-b2c8-4982-b6a0-2590c94b6000\n\nfolder/notebook 10% + a1b2c3d4\n=> folder-notebook-10percent-a1b2c3d4\n```\n\n## Optional Suffixes\n\n- File paths, when exposed and requested, append after the project segment as `/{encodeURIComponent(filePath)}`.\n- Cell or block anchors append after the UTM query string as `#anchor`.\n- Use Streamlit URLs returned by `create_streamlit_app` or `list_streamlit_apps`; do not assemble them from an app ID.\n- Use the data app URL from `dataApp.url` in `get_project`; never construct it.\n\n## UTM Parameters\n\nEvery project and notebook link gets these parameters. `utm_source` and `utm_campaign` depend on the host:\n\n| Host | `utm_source` | `utm_campaign` |\n| --- | --- | --- |\n| Codex | `codex` | `openaimcp` |\n| Claude Code | `claude-code` | `claudemcp` |\n| Claude Desktop or Cowork | `claude-desktop` | `claudemcp` |\n\n```text\nhttps://deepnote.com/<path>?utm_source={host_source}&utm_medium=mcp&utm_campaign={host_campaign}&utm_content={id}&utm_term={tool_name}\n```\n\n- `utm_content` is the notebook ID for notebook links and the project ID for project links.\n- `utm_term` is the tool that produced the link, such as `generate_project_url`, `list_projects`, `search`, `get_notebook`, or `create_notebook`, or `workspace_summary` for links built by the workspace summary.\n\n## Response Style\n\nReturn Markdown links with human-readable labels. Shown here with Codex values; in Claude Code use `utm_source=claude-code&utm_campaign=claudemcp` instead:\n\n```markdown\n[Project Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=project-id&utm_term=generate_project_url)\n[Notebook Name](https://deepnote.com/workspace/workspace-slug-workspace-id/project/project-id/notebook/notebook-id?utm_source=codex&utm_medium=mcp&utm_campaign=openaimcp&utm_content=notebook-id&utm_term=generate_project_url)\n```\n\nFor lists, inventories, and workspace summaries, put links in the `Project` or `Notebook` column and keep IDs in a separate column only when they help disambiguate. When a table has a `Notebook` column, hyperlink the notebook name itself. If a link cannot be built safely because workspace, project, or notebook data is missing, say which field is missing and how to resolve it.\n"
}

SHA-256 of public snapshot: f2be8ecda933b8980ed951ba7f45ab990b01dc000ae086a25a9c0fb5415d8b62