Cited project context for agents
What ScopeDocs is: cited project context for investigations, technical support, and AI agents. Keep decisions findable across handoffs, steering, and go-live.
How it helps: ScopeDocs is a knowledge source that also helps teams act. Humans confirm what is settled. Agents pull the same cited record over MCP for Cursor, Claude Code, Codex, ChatGPT, and custom stacks.
Markdown twin: product.md. Related: features, solutions, quickstart, pricing, homepage.
Discover the rest of ScopeDocs
Official twin: product.md. Site indexes: sitemap.xml · sitemap.md · llms.txt · llms-full.txt · blog RSS · AGENTS.md · MCP discovery. Product app: app.scopedocs.ai.
Paths from this page
- Homepage · index.md · How it works · Agents · Trust
- Features · features.md · Solutions · Pricing · pricing.md
- Onboarding · Incidents · Agents use case · Delivery handoffs
- Docs hub · Quickstart · quickstart.md · AI agents over MCP
- Generative documentation · Living documentation · Source-linked documentation
- Wiki vs living documentation · Generative docs vs wikis · MCP for engineering docs
- Vivian Nguyen Lin · Thao Ha · Radha Parikh
- About · about.md · Privacy · privacy.md · Terms
More from the blog
- Keep CRM change decisions findable
- CRM implementation handoff checklist
- Why CRM handoffs break between pods
- From discovery call to living CRM record
- Source-linked delivery record for a CRM rollout
- Implementation knowledge bases that stay current
- ERP consultancies and knowledge debt
- Why CRM and ERP firms abandon client wikis
- Living delivery records vs client wikis
- Consultant ramp time is a documentation problem
- Why CRM projects lose requirements
- ERP configuration rationale should not live in one head
- Where tribal knowledge lives in ERP and CRM
- When ERP and CRM customizations outpace docs
- Tracing customization rationale in Jira
- Knowledge base that updates automatically
- From PRs to living documentation
- Traceability and trust in AI docs
- When AI writes the docs, who checks?
- What to connect first
- Onboarding with context
- Why teams abandon wikis
How ScopeDocs works
Three steps. No second wiki to maintain by hand.
- Connect. Link the tools your team already uses with read-only OAuth.
- Stamp. Decisions become a durable, cited record. Humans approve what agents may trust.
- Ask. People search and chat in ScopeDocs. Agents help take the next step from the same answers over MCP.
| Step | What happens | Outcome |
|---|---|---|
| Connect | Read-only OAuth into GitHub, GitLab, Linear, Slack, Google Chat, Notion, Jira, Drive, Fathom, Datadog, Confluence, and more | Context starts flowing in without a migration project |
| Stamp | Claims link back to a PR, thread, ticket, or doc; humans confirm drafts | A verifiable living record instead of unverified AI prose |
| Ask | Search/chat for humans; MCP for Cursor, Claude Code, Codex, ChatGPT, and custom agents | One cited truth so people and agents act on the same record |
Step-by-step setup: quickstart. Definitions: generative documentation, living documentation, source-linked documentation.
Connect: tools you already use
Link GitHub, GitLab, Linear, Slack, Google Chat, Notion, Jira, Google Drive, Fathom, Datadog, Confluence, Microsoft Teams, monday.com, Supabase Database, and related systems with read-only OAuth. Setup is measured in minutes, not a migration project. You control which integrations are enabled and can disconnect them anytime.
Stamp: decisions with proof
Decisions become a durable, cited record. Every claim points back to a PR, chat thread, ticket, or doc so answers stay honest as the work changes. If the source is not there, ScopeDocs does not invent it. Humans approve, edit, or reject drafts before agents treat knowledge as settled.
Why that matters: how traceability improves trust in AI-generated documentation and when AI writes the docs, who checks the work.
Ask: then take the next step
Search and chat over project knowledge inside ScopeDocs. Agents reach the same cited decisions for Cursor, Claude Code, Codex, ChatGPT, and ScopeDocs via MCP. That is knowledge you can act on, not a black box. Permissions mirror your workspace so agents only see what your team can already see.
ScopeDocs vs a traditional wiki
| Need | Traditional wiki | ScopeDocs |
|---|---|---|
| Keep docs current | People remember to edit pages | Docs stay tied to merges, tickets, and decisions in connected tools |
| Verify a claim | Hope the page is right | Every material claim links to a source |
| Feed coding agents | Paste stale exports into prompts | Agents query the same governed record over MCP, ready to help take action |
| Hand off work | Tribal knowledge and outdated pages | Shared living context with citations for the next person or agent |
Deeper comparison: wiki vs living documentation and generative documentation vs wikis. Research: why teams abandon wikis and why CRM and ERP firms abandon client wikis.
What you connect
- Code and reviews: GitHub and GitLab pull requests, merge requests, and repository context
- Tickets and specs: Linear, Jira, and related trackers
- Decisions in chat: Slack and Google Chat threads and discussions
- Docs and wikis: Notion, Confluence, Google Drive
- Calls and ops: Fathom notes, Datadog signals, and more
Practical sequencing: documentation integrations: what to connect first.
Built for agents over MCP
Agents that help your pod take the next step, not just answer. The same governed record your team reads is available over MCP. Workspace MCP host pattern (shown in-product):
yourcompany.mcp.scopedocs.ai
Agent discovery: /.well-known/mcp.json. How it works: AI agents over MCP. Guide: MCP for engineering documentation. Homepage: agents section.
Trust and permissions
- Read-only OAuth access to connected tools
- Does not train public foundation models on connected workspace data
- Does not sell workspace data
- Permissions follow the tools your team already uses
- Works with private GitHub repositories and GitHub Enterprise
See Trust, Privacy, and the homepage FAQ.
Who it is for
Teams that lose client and delivery context across tools, handoffs, and rotating pods. ScopeDocs is for people who need a living knowledge source, and for agents that should help solve the next issue from cited decisions.
- Faster onboarding with sources attached
- On-call and incident context that has not drifted
- Delivery handoffs that keep the why
- Agent-ready project knowledge over MCP
Related reading: keep CRM decisions findable, implementation knowledge bases that stay current.
Product FAQ
What problem does ScopeDocs solve?
Important context gets trapped across chat, tickets, docs, and calls. ScopeDocs turns that work into one living, source-linked knowledge base people can trust and agents can act on, without maintaining a second system of record by hand.
Is ScopeDocs only for answering questions?
No. Answers matter, but the product is built so people and agents can act on cited context: handoffs, steering questions, change requests, and delivery work.
How is ScopeDocs different from a wiki?
Wikis depend on people remembering to update pages. ScopeDocs generates source-linked documentation from work already happening in connected tools, then keeps citations attached so the record stays verifiable as projects change.
Can agents use the same knowledge as humans?
Yes. People ask inside ScopeDocs; agents pull the same cited decisions over MCP for Cursor, Claude Code, Codex, ChatGPT, and custom stacks.
Is access write-capable by default?
No. Integrations use read-only OAuth (or credentials you supply). You choose what to connect.
How do we get started?
Follow the quickstart, request pricing on pricing, or email vivian@scopedocs.ai. No credit card required to talk to us.
Explore more
From the blog
- How to build an engineering knowledge base that updates automatically
- From GitHub PRs to living documentation
- How traceability improves trust in AI-generated docs
- Why teams abandon wikis
- Documentation integrations: what to connect first
- Onboarding with context
- When AI writes the docs, who checks the work?