Living documentation for product and delivery teams. ScopeDocs connects Slack, tickets, docs, and calls into a sourced project record, and a knowledge graph over that work, so people and agents can open answers with sources attached.

How does ScopeDocs work?

Connect your tools with read-only OAuth, stamp decisions as work happens with citations back to the original PR, thread, or ticket, and ask with proof attached. Humans confirm what matters before agents treat knowledge as settled.

What sources can you connect?

Slack, GitHub, Jira, Linear, Confluence, Google Drive, Notion, Fathom call notes, Datadog, Microsoft Teams, monday.com, Supabase Database, and more, across the tools your team already lives in.

Can I use ScopeDocs with AI agents?

Yes. People and agents read the same record. Agents ask what your team asks, with citations, not a stale paste. Cursor, Claude Code, ChatGPT, and custom stacks connect over MCP.

Do you offer an MCP server?

Yes. Through MCP, agents in Cursor, Claude Code, ChatGPT, or your own stack can pull current decisions and proof at runtime from the same cited workspace record humans use in ScopeDocs.

Your workspace content stays in your workspace. We do not train public foundation models on your connected data, and we do not sell that data. Permissions follow the tools you already use. See Trust and the Privacy Policy for the full picture.

Does ScopeDocs work with private or enterprise GitHub?

Yes. ScopeDocs works with private GitHub repositories and GitHub Enterprise. Access is read-only via OAuth and follows your existing repo permissions.

How does pricing work?

Pricing fits team size, sources, and agent use. Request a quote on the pricing page or book a demo and we will match you with the right plan. There is no public fixed dollar price list because every workspace footprint differs.

MCP for engineering documentation

Last updated August 2026

Model Context Protocol (MCP) is a standard way for AI clients to connect to tools and data sources. For engineering documentation, MCP means coding agents can query a living, source-linked knowledge base and get answers with citations, instead of inventing context from a stale Confluence export.

Why MCP matters for docs

Engineering teams already live in agents: Cursor, Claude Code, ChatGPT, and internal assistants. Those agents are only as good as the context they receive. Pasting a wiki page into a prompt does not scale, and it fails silently when the page is weeks out of date. MCP gives agents a durable connection to a documentation system of record so every session can start from current decisions with sources attached.

ScopeDocs is living, source-linked documentation for engineering teams. People ask inside the product. Agents pull the same cited record over MCP. Integrations use read-only OAuth so you choose what to connect without granting write access to production tools.

What agents get from documentation MCP

Current project decisions: what shipped, what was deferred, and why
Citations: links back to PRs, tickets, Slack threads, or related artifacts
Shared truth: the same record humans already confirmed in ScopeDocs
Less hallucination risk: answers are grounded in checkable origins, not orphaned prose

How documentation MCP fits the workflow

Connect work tools: index GitHub, Linear, Slack, and related systems via read-only OAuth
Stamp and confirm: capture claims with who decided and where evidence lives
Connect agents: point Cursor, Claude Code, ChatGPT, or custom clients at your workspace MCP host (shown in-product)
Ask with proof: agents retrieve cited context in the coding loop; humans can audit the same sources

Setup details live in MCP for agents and the quickstart. Discovery metadata: .well-known/mcp.json.

MCP vs dumping docs into the prompt

Prompt dumps are one-shot and go stale the moment the next PR merges. MCP is a live channel: agents request what they need when they need it. Combined with source-linked documentation, that channel carries not only text but provenance. The pairing matters: living docs for freshness, citations for trust, MCP for agent access.

Security posture teams should expect

Private engineering context should never sit on a public anonymous endpoint. ScopeDocs workspace MCP requires app authentication. Connected tools use read-only OAuth (or credentials you supply). You control what gets indexed. See privacy and product.

FAQ

Which agents work with documentation MCP?

Any MCP-capable client can connect when configured for your workspace. Common examples include Cursor, Claude Code, ChatGPT, and custom agent stacks.

Does MCP replace human documentation readers?

No. MCP extends the same record to agents. Engineers still search and chat in ScopeDocs. Agents and humans share one cited knowledge base.

How is this different from generic RAG over a wiki?

RAG over a wiki can retrieve stale pages with no obligation to cite the originating PR or thread. Documentation MCP over living, source-linked docs keeps retrieved answers attached to checkable work.