Connect contextrepo.com and your agent gets 29 tools, among them add_to_collection, create_collection, create_document. It answers at https://contextrepo.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 11 of 11 times since 4 September 2026; the last check, on 25 October 2026, succeeded.
Model Context Protocol server for contextrepo.com, exposing 29 tools.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_to_collection | Add documents or prompts to a collection. Requires the `documents.write` API-key scope (collections share the documents.write scope). Inputs: collectionId, itemIds, itemType |
create_collection | Create a new collection to organize prompts and documents. Requires the `documents.write` API-key scope (collections share the documents.write scope -- see `shared/api-key-permissions.ts`). Inputs: name, description, color, icon, tags |
create_document | Create a new text document. Requires the `documents.write` API-key scope. The content field is limited to ~900 KB; the overall request body is capped at 2 MB. Inputs: title, content, tags |
create_prompt | Create a new prompt template. Requires the `prompts.write` API-key scope. Inputs: title, description, content, tags |
deep_expand | Navigate the document hierarchy from a chunk in 5 directions: up (parent), down (children), next (next sibling under the same parent), previous (previous sibling under the same parent), surrounding (context window — same-parent siblings; on Inputs: chunkId, direction, count |
deep_read | Retrieve a single document chunk with full content and hierarchy metadata. Use after deep_search (to inspect a result in detail) or deep_expand (to examine a navigated chunk). Returns complete text plus structural position: sectionPath, chu Inputs: chunkId |
deep_search | Search within document content using vector similarity and return ranked, hierarchical chunks. Unlike find_items (which returns item-level catalog results across prompts, documents, and collections), deep_search returns granular content fra Inputs: query, limit, sessionId, collectionId, documentId |
delete_collection | Delete a collection. Items in the collection are NOT deleted, only the collection itself. Requires the `documents.write` API-key scope (collections share the documents.write scope). Inputs: collectionId |
delete_document | Permanently delete a document. This action cannot be undone. Requires the `documents.write` API-key scope. Inputs: documentId |
delete_prompt | Permanently delete a prompt. This action cannot be undone. Requires the `prompts.write` API-key scope. Inputs: promptId |
fetch | Retrieve the full content of a single prompt, document, or collection by id (returned from `search`). Returns markdown text plus a citation URL compatible with ChatGPT Apps Company Knowledge. The id format is `<type>_<convexId>` (e.g., "pro Inputs: id |
find_items | Search the user's own workspace for prompts, documents, and collections matching a query. Read-only. Returns titles, IDs, and relevance scores. Literal mode (semantic=false) searches titles, descriptions, and indexed document body text via Inputs: query, type, semantic, tags |
get_collection | Get details of a specific collection including its items Inputs: collectionId, includeItems |
get_document | Get a document with its canonical revision, content hash, change time, and exact ETag. Inputs: documentId |
get_document_versions | Get the version history of a document. Shows all previous versions with change logs. Inputs: documentId |
get_prompt_versions | Get the version history of a prompt. Shows all previous versions with change logs. Inputs: promptId |
get_user_info | Gets information about the authenticated Context Repo user |
list_collections | List all collections belonging to the authenticated user Inputs: search, limit, cursor, tags |
list_documents | List all documents belonging to the authenticated user Inputs: search, limit, cursor, tags |
read_prompt | Get the full details of a specific prompt including its content and variables Inputs: promptId |
reason | Ask a question and get a synthesized, cited answer composed across your documents -- not a list of chunks. Returns the answer with inline citations to the exact chunks used, an explicit list of gaps (what your repository does NOT contain ab Inputs: query, limit, documentId, collectionId |
remove_from_collection | Remove documents or prompts from a collection. Requires the `documents.write` API-key scope (collections share the documents.write scope). Inputs: collectionId, itemIds, itemType |
restore_document_version | Restore a document through the canonical revision path. Pass expectedRevision for a same-invocation ETag check, and pass idempotencyKey plus the active leaseId and leaseFence when coordination is enabled. A legacy partial snapshot returns a Inputs: documentId, versionId, expectedRevision, idempotencyKey, leaseId, leaseFence |
restore_prompt_version | restore_prompt_version restores versioned content, parameters, and variables as a new version. Prompt title, description, tags, visibility, and other unversioned metadata remain at their current values. Requires the `prompts.write` API-key Inputs: promptId, versionId |
search | Search the user's Context Repo workspace for prompts, documents, and collections matching a query. Returns a flat list of citation-ready results compatible with ChatGPT Apps Company Knowledge. Each result has an opaque `id` (pass it to `fet Inputs: query |
search_prompts | List prompts in the authenticated user's workspace. Full-text (literal) match on title, description, and content. For semantic / natural-language matching of prompts, use find_items. Inputs: search, limit, cursor, tags |
update_collection | Update a collection's metadata. Requires the `documents.write` API-key scope (collections share the documents.write scope). Inputs: collectionId, name, description, color, icon, tags |
update_document | Update canonical document fields. Any changed field creates a revision; an exact unchanged update is a no-op. Pass expectedRevision for a same-invocation ETag check, and pass idempotencyKey plus the active leaseId and leaseFence when coordi Inputs: documentId, title, content, contentHtml, rawHtml, sourceUrl |
update_prompt | Update an existing prompt. Only provide the fields you want to change. Updates that change `content` create a new version row in the prompt history (inspect with get_prompt_versions, roll back with restore_prompt_version). Metadata-only edi Inputs: promptId, title, description, content, changeLog, tags |
Every block below points at https://contextrepo.com/mcp. Pick your client and copy.
claude mcp add --transport http contextrepo-com https://contextrepo.com/mcp
{
"mcpServers": {
"contextrepo-com": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://contextrepo.com/mcp"]
}
}
}{
"mcpServers": {
"contextrepo-com": {
"url": "https://contextrepo.com/mcp"
}
}
}{
"servers": {
"contextrepo-com": {
"type": "http",
"url": "https://contextrepo.com/mcp"
}
}
}{
"context_servers": {
"contextrepo-com": {
"url": "https://contextrepo.com/mcp"
}
}
}{
"mcpServers": {
"contextrepo-com": {
"serverUrl": "https://contextrepo.com/mcp"
}
}
}{
"mcpServers": {
"contextrepo-com": {
"url": "https://contextrepo.com/mcp"
}
}
}name: contextrepo.com
version: 0.0.1
schema: v1
mcpServers:
- name: contextrepo.com
type: streamable-http
url: https://contextrepo.com/mcp{
"mcpServers": {
"contextrepo-com": {
"httpUrl": "https://contextrepo.com/mcp"
}
}
}{
"mcpServers": {
"contextrepo-com": {
"type": "http",
"url": "https://contextrepo.com/mcp"
}
}
}{
"mcpServers": {
"contextrepo-com": {
"url": "https://contextrepo.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcontextrepo.com%2Fmcp&type=streamable_http&id=contextrepo-com&name=contextrepo.com
It answered our last check on 25 October 2026 in 443 ms. Over 11 checks since 4 September 2026 it answered 11. Status here comes from Neuronto's own probes, not from the publisher.
29, as returned by the server's own tools/list on 1 September 2026: add_to_collection, create_collection, create_document, create_prompt, deep_expand, deep_read, deep_search, delete_collection, and 21 more.
It answered our last check on 25 October 2026 in 443 ms. Over 11 checks since 4 September 2026 it answered 11.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://contextrepo.com/mcp. 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: ora.ai. Endpoint host: contextrepo.com. ARD identifier: urn:air:ora.ai:mcp:contextrepo.com-mcp-0.
First indexed 1 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.