# Everything you want your AI to know, in one place.

> Stop losing your best AI work.

Save the documents, research, and answers worth keeping. Organize them into collections. Use them in ChatGPT, Claude, Cursor, Grok, and more.

[Start free](https://contextrepo.com/pricing) · [See how it works](https://contextrepo.com/#how)

- **Collections.** Group what belongs together into grounded context your tools can pull.
- **Documents.** Write from any agent or app. Read what you save anywhere your work takes you.
- **Reusable prompts.** Save the instructions you keep rewriting. Version and parameterize them.
- **MCP/API server.** Full CRUD plus retrieval over the repository, OAuth hosted, API key local.
- **Deep search.** Retrieve only the passage your agent needs, then expand around it when more context matters.

## Your AI knowledge has a shelf life of one tab.

Every AI tool stores context differently. None of them talk to each other. Every new conversation starts from zero.

- **Buried in a chat.** Your best prompt is in a ChatGPT conversation from last Tuesday.
- **Gone with the session.** That research doc you uploaded to Claude disappeared when the session ended.
- **Stuck in one project.** The system prompt you perfected in Cursor sits in a project you have not opened in weeks.

Context Repo keeps your [AI context](https://contextrepo.com/resources/what-is-an-ai-context-repo-for-agents) together: collections, documents, and prompts for the tools you connect.

For developers: MCP, the REST API, and the [CLI](https://contextrepo.com/cli) bring that context into agents, apps, and custom workflows.

## What you keep

**A home for everything worth reusing.** One place for the collections, documents, and prompts you keep coming back to. Curate them once, then reach them from every AI tool you use.

### Collections

Group what belongs together. Each collection becomes grounded context your connected AI tools can pull, the same way your agents do.

- Grounded context for connected MCP clients
- Hierarchical organization
- Share read-only with a link

MCP verbs: `list`, `get`, `create`, `update`, `delete`, `add`, `remove`

### Documents

Bring in the source material worth keeping. Process 75+ file formats or scrape a page, and it is ready for any agent to read.

- 75+ file formats (LlamaIndex)
- Public page capture on Pro Max and Ultimate
- Real-time processing status

MCP verbs: `list`, `get`, `create`, `update`, `delete`

### Reusable prompts

Save the instructions you keep rewriting. Version them, parameterize them, and call them from any tool.

- Snapshot history and non-destructive restore
- Placeholders with ${syntax}
- Caller-managed placeholder values

MCP verbs: `list`, `get`, `create`, `update`, `delete`

## Curate once. Reach it everywhere you work, and so can your agents.

The dashboard is where you curate. The value lands inside your tools. One connection over [MCP](https://contextrepo.com/resources/how-mcp-servers-connect-ai-agents-to-knowledge-bases), the API, or OAuth reaches every client you use, and every agent you run.

### ChatGPT (OAuth connection)

Sign in with your Context Repo account inside ChatGPT. Your documents and prompts appear in the conversation.

[Connect ChatGPT](https://contextrepo.com/chatgpt-plugin)

### Claude Desktop (MCP server config)

Add Context Repo with a short JSON block. Paste it into claude_desktop_config.json.

[View config](https://contextrepo.com/docs/mcp/setup-guides/claude-desktop)

### Cursor (One-click deep link)

Click once to configure Context Repo in your Cursor settings. No manual JSON editing.

Install to Cursor:

```
cursor://anysphere.cursor-deeplink/mcp/install?name=context-repo&config=eyJ1cmwiOiJodHRwczovL2NvbnRleHRyZXBvLmNvbS9tY3AifQ%3D%3D
```

**29** MCP tools · **35** API endpoints · **75+** file formats · **90+** MCP clients (est.)

**29** MCP tools behind one URL. Full CRUD over collections, documents, and prompts, plus retrieval and a cited `reason` answer.

The same repository is reachable over the REST API for builders and inside the dashboard for people. Whatever you save in one place is what every connected client reads.

No copy-paste between tools. No re-uploading the same file to three assistants. One connection, kept current.

## Built for agents

**Agent-grade by design.** The openness that puts your context inside your apps is the same thing that lets your agents consume it. One repository, reachable over MCP and the REST API.

An illustrative `reason` exchange:

- Question: What did we settle on for auth token rotation?
- Answer: You standardized on Clerk session JWTs for first-party callers and bcrypt-hashed keys for machines. For unscoped questions, retrieval stays quiet below a relevance floor instead of bluffing an answer from weak matches.
- Citations: Auth model, API keys, Security notes
- Gaps: The retrieved evidence doesn't establish refresh-token expiry windows.

Ask a question and get a best-effort cited answer with non-exhaustive limitations. Disagreements appear as ordinary cited statements in the answer. Reachable from connected MCP clients or the REST API.

### Reasoned answers

Ask a question and get a best-effort cited answer with inspectable sources and non-exhaustive limitations.

Related: `reason`

### Deep search

Hierarchical retrieval lands on the exact passage, then walks parent, sibling, and surrounding chunks without re-querying.

Related: `deep_search`, `deep_read`, `deep_expand`

### Version history

Prompt content edits and changed canonical document fields create history. Restore an earlier snapshot without deleting the intervening versions.

Related: `get_*_versions`, `restore_*_version`

### Broad ingest

The Context Repo ingestion and upload pipeline supports 75+ file formats. MCP create_document accepts plain text or Markdown.

Related: `create_document`, `scrape`

### MCP server

Full CRUD plus retrieval over the repository, with ChatGPT auto-detect via the search and fetch aliases.

Related: `search`, `fetch`

### Collections as context

Read collection members directly, or pass collectionId to deep_search or reason to restrict document retrieval.

Related: `get_collection`, `deep_search`, `reason`

## Search that lands on the exact passage.

Search is not a flat list of hits. Deep Search returns ranked, [hierarchical chunks](https://contextrepo.com/resources/why-hierarchical-retrieval-finds-more-than-flat-rag) with section paths and sibling navigation, so your AI client jumps to the passage that answers the question, then expands up, down, or sideways for context.

- Hierarchical vector search down to paragraph level
- Section paths and sibling navigation in every hit
- Expand a hit without re-running the query

## See what changed. Restore what worked.

Prompt content updates and changed canonical document fields create history; unchanged saves are no-ops. Restore an earlier snapshot in one click without deleting the versions that followed it.

- Line-level visual diffs between recorded versions
- Non-destructive restore keeps the intervening versions
- History over MCP and the REST API, not just the dashboard

## The doors you build through.

Web dashboard for People. MCP server for agents. REST API and CLI for builders. Chrome extension for capture.

### Web dashboard

Where people curate. Upload, organize, search, and share. [Open the dashboard](https://contextrepo.com/dashboard)

### MCP server

Where agents read and write. One URL for Claude, Cursor, ChatGPT, and other MCP clients. [Install the MCP server](https://contextrepo.com/mcp-server)

### REST API and CLI

Where builders integrate. The same repository over plain HTTP, or from any shell. [Get the CLI](https://contextrepo.com/cli)

### Chrome extension

Where capture happens. Save a page or a chat without leaving the tab. [Get the extension](https://contextrepo.com/chrome-extension)

## One store. Every AI tool. Yours and your agents'.

The documents, research, and prompts worth reusing, versioned, searchable, and available from every AI tool you use. Start free today.

[Start free](https://contextrepo.com/pricing) · [Install MCP Server](https://contextrepo.com/mcp-server) · MCP URL: `https://contextrepo.com/mcp`

## For agents

### Connect over MCP

Remote clients that implement MCP OAuth connect directly:

```
URL: https://contextrepo.com/mcp
Transport: streamable-http
Auth: OAuth2 or Context Repo API key
```

Clients that send headers can use an API key instead:

```json
{
  "mcpServers": {
    "context-repo": {
      "url": "https://contextrepo.com/mcp",
      "headers": {
        "Authorization": "API-Key gm_your_api_key_here"
      }
    }
  }
}
```

Clients that launch a local command use the `context-repo-mcp` v3 stdio bridge (Node.js 18+) with an API key from Dashboard > Settings > API Keys:

```json
{
  "mcpServers": {
    "context-repo": {
      "command": "npx",
      "args": ["-y", "context-repo-mcp"],
      "env": {
        "CONTEXTREPO_API_KEY": "gm_your_api_key_here"
      }
    }
  }
}
```

### What the repository holds

- Prompts: version-controlled templates with `${variableName}` placeholders stored verbatim. Placeholder values are caller-managed; Context Repo does not substitute or execute templates.
- Documents: the Context Repo ingestion and upload pipeline supports **75+ file formats** via LlamaIndex (PDF, Word, Excel, PowerPoint, images with OCR, code files). MCP `create_document` accepts plain text or Markdown. Public page capture runs through Firecrawl on Pro Max and Ultimate.
- Collections: read collection metadata and up to 50 member items with `get_collection`, and scope document retrieval with the `collectionId` accepted by `deep_search` and `reason`. Tags work across collections, prompts, and documents; agents can filter retrievals by any combination of tags using AND semantics.

### Search

- Semantic search: 1536-dimension vector search across all content.
- Literal search: exact substring matching across titles, descriptions, and indexed document body text via hierarchical chunks (full-body literal matching, eventually consistent with chunking).
- Deep Search: hierarchical chunk navigation inside documents (document, section, paragraph).
- Session-aware deduplication filters out chunks already returned in the same session; once matching chunks are exhausted, the search returns no results.

### Access points

| Channel | Description |
|---------|-------------|
| Web Dashboard | Create, edit, and organize content with real-time sync |
| MCP Server | 29 tools over authenticated Streamable HTTP or the local stdio bridge |
| ChatGPT App | OAuth for direct access inside ChatGPT |
| Grok | Dedicated hosted OAuth endpoint at https://contextrepo.com/grok-mcp |
| REST API | 35 REST operations with Bearer JWT and API key authentication |
| CLI | The same REST operations from a shell, a script, or CI |
| Chrome Extension | Visible-chat and selected-content writes, plus public-page capture through Firecrawl |

90+ clients exist in the broader MCP ecosystem; transport and authentication support varies.

### Links

- Pricing: https://contextrepo.com/pricing
- Solutions: https://contextrepo.com/solutions
- MCP Server: https://contextrepo.com/mcp-server
- Documentation: https://contextrepo.com/docs
- GitHub: https://github.com/Gitmaxd/context-repo-mcp
- npm: https://www.npmjs.com/package/context-repo-mcp

## Feedback & Scan Hooks

- Feedback: report issues or feature requests via [GitHub Issues](https://github.com/Gitmaxd/context-repo-mcp/issues).
- Agent scan tools (Ora.run, Tavily, Perplexity) can scan this response and the linked surfaces to discover every Context Repo MCP tool and REST endpoint.
- Every endpoint emits `Content-Signal: ai-train=no, search=yes, ai-input=yes` to communicate crawler policy.
- Site-wide context pack: https://contextrepo.com/llms.txt | Full pack: https://contextrepo.com/llms-full.txt | Agent catalog: https://contextrepo.com/agent

## Verbatim llms.txt

The full site-wide llms.txt context pack is embedded below for agents that prefer a single-fetch consumption pattern.

```markdown
# Context Repo

> Context Repo is the AI Context Repo for agents. Save prompts and
> documents with version history, organize them in collections, and
> retrieve them from ChatGPT or connected clients through a 29-tool MCP
> server. Its `search` and `fetch` tools provide
> ChatGPT App compatibility through OpenAI Apps SDK Company Knowledge.

- Prompt templates with `${variable}` placeholders stored verbatim;
  Context Repo does not substitute or execute them
- Semantic search across all content (1536-dimension vectors)
- Hierarchical Deep Search inside document content (chunk-level)
- Snapshot history and non-destructive restore for prompts and documents
- The Context Repo ingestion and upload pipeline supports 75+ file formats via LlamaIndex Cloud. MCP `create_document` accepts plain text or Markdown.
- Web scraping via Firecrawl integration (Pro Max and Ultimate)
- 35 REST API operations under /v1 with Bearer JWT or API-key auth

## When to use Context Repo

Use Context Repo when an agent needs to (a) retrieve a versioned prompt
template, (b) search across a user's stored prompts/documents/collections,
(c) persist a new prompt or document for later reuse, (d) sync context
across Claude, Cursor, ChatGPT, Grok, VS Code, Grok Bot, Factory, or Amp,
(e) save conversations, decisions, and session handoffs from ChatGPT,
Claude, or another connected agent, then find and reuse them from other
connected clients, (f) save a public web page by URL and refresh it later,
or (g) share a prompt or document through a read-only public link.

**When not to use:** Context Repo searches your stored context, not the
open web, and it runs retrieval for you rather than acting as a raw vector
store. Accounts belong to one person today, with no org or team seats.
Several agents can share one account safely, each with its own scoped key;
revision checks and optional document leases coordinate their edits.

## Getting Started

- [MCP Server Setup](https://contextrepo.com/mcp-server): Connect Context Repo to Claude, Cursor, or another client with compatible transport and authentication support
- [Quickstart](https://contextrepo.com/docs/getting-started/quickstart): 60-second integration walkthrough — sign up, create your first prompt, connect an AI assistant
- [ChatGPT App](https://contextrepo.com/chatgpt-plugin): Native ChatGPT integration via OAuth
- [Grok Connector](https://contextrepo.com/docs/integrations/grok): Add Context Repo to Grok with the dedicated https://contextrepo.com/grok-mcp OAuth entrypoint
- [Chrome Extension](https://contextrepo.com/chrome-extension): Save visible ChatGPT or Claude conversations, capture public page URLs through Firecrawl, or submit selected page content
- [User Documentation](https://contextrepo.com/docs): Setup guides, dashboard reference, MCP and REST integration docs, and FAQ
- [Ask the Docs](https://ask.contextrepo.com): Conversational AI that answers questions from the Context Repo documentation
- [Full Agent Context (`llms-full.txt`)](https://contextrepo.com/llms-full.txt): Single-fetch knowledge pack for agents

## Features

- [Document Management](https://contextrepo.com/agent/features/documents): Store knowledge artifacts with canonical revisions, ETags, no-op detection, and optional fenced lease coordination
- [Semantic Search](https://contextrepo.com/agent/features/search): Vector and keyword search across all prompts, documents, and collections
- [Deep Search](https://contextrepo.com/agent/features/deep-search): Hierarchical navigation inside document content with chunk-level precision
- [Reasoning](https://contextrepo.com/agent/features/reason): Use `reason` to get one best-effort synthesized answer over stored document content with inline citations and non-exhaustive limitations. Disagreements appear as ordinary cited statements in the answer. Read-only; does not persist.
- [Collections](https://contextrepo.com/agent/features/collections): Organize prompts and documents into named folders; inspect members directly, or scope document retrieval with `deep_search` and `reason`
- [Prompt Management](https://contextrepo.com/agent/features/prompts): Create, version, and share prompt templates with placeholder syntax
- [MCP Server](https://contextrepo.com/mcp-server): 29 tools with OAuth and API key authentication, including OpenAI Apps SDK Company Knowledge-compatible `search`/`fetch` and `reason` for synthesized, cited answers across your documents
- [REST API](https://contextrepo.com/agent/features/api): 35 HTTP operations under /v1 with Bearer JWT and API key auth

## Developer Resources (HTML reference)

- [REST API Documentation](https://contextrepo.com/docs/api): Human-readable REST API reference — base URL derivation, response envelope, error format, CORS policy, rate limits
- [REST API Authentication](https://contextrepo.com/docs/api/authentication): Bearer JWT (Clerk) and API-Key setup with example requests
- [REST API Endpoints](https://contextrepo.com/docs/api/endpoints): Full reference for all 35 REST operations with request/response examples
- [API Versioning & Deprecation Policy](https://contextrepo.com/docs/api/versioning): /v1 URL-versioning contract — additive-only changes within a major, side-by-side majors, six-month sunset runway signaled with Deprecation and Sunset headers (RFC 8594, RFC 9745)
- [Webhooks](https://contextrepo.com/docs/webhooks): Outbound workspace webhooks are not currently available; this page documents status and current alternatives

## API Specification

- [OpenAPI 3.1 (JSON)](https://contextrepo.com/openapi.json): Machine-readable spec for the 35 REST operations
- [OpenAPI 3.1 (YAML)](https://contextrepo.com/api/openapi.yaml): YAML mirror of the OpenAPI spec
- [API Catalog (RFC 9727)](https://contextrepo.com/.well-known/api-catalog): Linkset of REST artifacts
- [Markdown homepage (`index.md`)](https://contextrepo.com/index.md): Plain-markdown homepage rendering
- [Markdown pricing (`pricing.md`)](https://contextrepo.com/pricing.md): Plain-markdown pricing reference

## Markdown pages

Markdown versions of the marketing pages, with the same sections and words as the web page plus a "For agents" section. Requesting the web URL with `Accept: text/markdown` or `?mode=agent` redirects here.

- [Home](https://contextrepo.com/agent/pages/home): Markdown version of https://contextrepo.com/
- [Solutions](https://contextrepo.com/agent/pages/solutions): Markdown version of https://contextrepo.com/solutions
- [Pricing](https://contextrepo.com/agent/pages/pricing): Markdown version of https://contextrepo.com/pricing
- [MCP Server](https://contextrepo.com/agent/pages/mcp-server): Markdown version of https://contextrepo.com/mcp-server

## MCP Server

- [MCP Endpoint](https://contextrepo.com/mcp): Streamable HTTP transport. Clients that send `Accept: text/event-stream` receive SSE-framed JSON-RPC; JSON-only clients receive a single chunked response (an Accept-shim unframes the SSE on the wire automatically).
- [Grok MCP Endpoint](https://contextrepo.com/grok-mcp): Auth-required compatibility entrypoint exposing the same 29 hosted tools
- [MCP Discovery](https://contextrepo.com/.well-known/mcp.json): MCP server capabilities and connection info (SEP-1649)
- [MCP Server Card](https://contextrepo.com/.well-known/mcp/server-card.json): All 29 tool registrations with descriptions
- [Agent Catalog](https://contextrepo.com/agent): Machine-readable capability catalog (JSON or markdown via Accept)
- [Docs MCP Endpoint](https://contextrepo.com/docs-mcp): Public, no sign-in. Searches and reads the Context Repo documentation (search_docs, read_docs_page, list_docs_pages); separate from the account MCP above

## Agent Discovery

- [OpenAI ai-plugin manifest](https://contextrepo.com/.well-known/agent.json): Agent discovery file
- [A2A Agent Card](https://contextrepo.com/.well-known/agent-card.json): Agent-to-Agent skills catalog
- [OAuth Authorization Server (RFC 8414)](https://contextrepo.com/.well-known/oauth-authorization-server): Clerk-backed authorization-server metadata
- [OAuth Protected Resource — REST (RFC 9728)](https://contextrepo.com/.well-known/oauth-protected-resource/v1): Scopes for the /v1 REST API
- [OAuth Protected Resource — MCP (RFC 9728)](https://contextrepo.com/.well-known/oauth-protected-resource/mcp): OAuth scopes for the MCP transport
- [OAuth Protected Resource — Grok MCP (RFC 9728)](https://contextrepo.com/.well-known/oauth-protected-resource/grok-mcp): OAuth metadata for the Grok compatibility entrypoint

## Resources

In-depth articles on AI context management, MCP servers, prompt
versioning, semantic search, and integrations across Claude, Cursor,
and ChatGPT.

- [What is an AI Context Repo for Agents?](https://contextrepo.com/resources/what-is-an-ai-context-repo-for-agents): What an AI context repository is, what belongs inside it, and how humans and connected agents retrieve shared prompts, documents, and collections
- [Prompt and Document Management for AI Agents](https://contextrepo.com/resources/prompt-and-document-management-for-ai-agents): How a context repository handles version snapshots, stored prompt variables, caller-managed substitution, semantic search, and broad upload ingestion alongside text/Markdown MCP document creation
- [How MCP Servers Connect AI Agents to Knowledge Bases](https://contextrepo.com/resources/how-mcp-servers-connect-ai-agents-to-knowledge-bases): What an MCP server is, what Context Repo's 29-tool server exposes, and what clients need to connect
- [Semantic Search and Deep Search: Two Retrieval Layers](https://contextrepo.com/resources/semantic-search-and-deep-search-two-retrieval-layers): Vector similarity at the catalog level, hierarchical chunk navigation inside documents, and how to pick the right retrieval surface for an agent's question
- [Using Context Repo with Claude, Cursor, and ChatGPT](https://contextrepo.com/resources/using-context-repo-with-claude-cursor-and-chatgpt): How a single context repository travels across Cursor, Claude Desktop, Claude.ai, and ChatGPT, with workflows for the engineer, the researcher, and the operator

Resources index: https://contextrepo.com/resources/llms.txt
Resources RSS: https://contextrepo.com/resources/feed.xml

## Modular Sections

- [Documentation index](https://contextrepo.com/docs/llms.txt): Section-scoped llms.txt for the user-documentation surface
- [Documentation full text](https://contextrepo.com/docs/llms-full.txt): Every docs page as Markdown in one file; any single docs page is its URL plus `.md`
- [REST API index](https://contextrepo.com/api/llms.txt): Section-scoped llms.txt for the /v1 REST API surface
- [Developers index](https://contextrepo.com/developers/llms.txt): Section-scoped llms.txt for agent / MCP / SDK integrators
- [Resources index](https://contextrepo.com/resources/llms.txt): Section-scoped llms.txt for long-form articles

## Constraints & Rate Limits

- Rate limits (per authenticated user, sliding window): scrape 10/60s, api 100/60s, readonly 120/60s. Responses may include `X-RateLimit-*` metadata. On `429`, honor `Retry-After`.
- Context Repo generates 1536-dimensional embeddings with text-embedding-3-small; public REST and MCP inputs do not accept caller-supplied vectors.
- Prompt and direct document content inputs: 900,000 UTF-8 bytes per field; whole request body: 2,000,000 bytes.
- Pagination: opaque base64 cursors; default page size 20, max 100.
- DELETE responses are 200 + `{success, id}` (not 204) for MCP-client compatibility.

## Document Revision Protocol

- MCP `update_document` and `restore_document_version` require `expectedRevision` from `get_document` or the latest successful document acknowledgement.
- Each MCP invocation makes exactly one REST write with no preflight GET. On `REVISION_MISMATCH`, read again; if the intended state is already present, stop, otherwise reapply the change to the latest content and retry with its revision. Documents using `lease_required` managed editing must use the REST coordination workflow.
- The remaining protocol details in this section apply to raw REST clients.
- Reads return canonical revision metadata and `ETag`; no-op writes do not create another revision.
- PATCH and restore accept either `If-Match` or body `expectedRevision`; when both are supplied, their revisions must agree and the header's content hash is also checked. Preconditions and `Idempotency-Key` remain optional in standard mode.
- `GET|PUT|DELETE /v1/documents/{id}/coordination` inspect, enable, or disable `lease_required` coordination.
- `POST /v1/documents/{id}/coordination/lease` acquires, renews, or releases a fenced lease and requires `Idempotency-Key`.
- Managed PATCH and restore require either revision precondition above plus `Idempotency-Key`, `X-ContextRepo-Lease-Id`, and `X-ContextRepo-Lease-Fence`.
- Refresh and coordination-policy operations retain their existing preconditions: managed refresh requires `If-Match`, the key, and both lease headers; policy changes require the exact current ETag in `If-Match`.
- Retry the identical operation with its original revision, key, payload, lease fields, and original precondition representation (`If-Match` or body `expectedRevision`). Do not replace the revision or key to recover an uncertain result. Matching receipts are retained for 24 hours from creation. Reconcile uncertain operations by reading the document and history before taking further action.
- Compact update/restore acknowledgements include `noop`; partial legacy restores warn `LEGACY_PARTIAL_SNAPSHOT`.
- Plan limits: requests over a plan allowance return `402` with `error.reason` `PLAN_REQUIRED`, `FEATURE_NOT_IN_PLAN`, or `QUOTA_EXCEEDED`. `503` with `ENTITLEMENT_UNAVAILABLE` is temporary; honor `Retry-After`. `GET /v1/user/me` returns the current plan and usage.

## Pricing

- [Plans & Pricing](https://contextrepo.com/pricing): 7-day free trial available on the Pro and Pro Max plans. Pro ($9.99/mo) includes 29 MCP tools, the ChatGPT App, Chrome Extension, and version history. Pro Max ($19.99/mo) has 2× the Pro allowances, plus web scraping. Ultimate ($99.99/mo) has 10× the Pro allowances, plus web scraping. Every plan limit: https://contextrepo.com/pricing.md

## SDK & packages

- [npm: context-repo-mcp](https://www.npmjs.com/package/context-repo-mcp): Official MCP server package (`npx context-repo-mcp`)
- [GitHub: Gitmaxd/context-repo-mcp](https://github.com/Gitmaxd/context-repo-mcp): MCP server source code
- [Chrome Web Store](https://chromewebstore.google.com/detail/context-repo/hlmpbcbphnhecbcakbnlobgighfnlafi): Context Repo Chrome extension

## Contact

- Email: support@contextrepo.com
- X / Twitter: https://x.com/contextrepo
- GitHub: https://github.com/Gitmaxd/context-repo-mcp
- Status: https://contextrepo.com/status
- About: https://contextrepo.com/about
- Public agent rules: https://contextrepo.com/AGENTS.md

## Optional

- [Privacy Policy](https://contextrepo.com/policies/privacy)
- [Terms of Service](https://contextrepo.com/policies)
```