# Scribe MCP > Scribe connects your company's process documentation library directly to your AI agent. You can ask natural language questions and get answers pulled from step-by-step guides (Scribes) or general knowledge pages. It lets you search across all documents, filter by team, check recent changes, and audit what content exists in your organization. ## Overview - **Category:** productivity - **Price:** Free - **Tags:** scribe, process-documentation, knowledge-base, step-by-step-guides, sop ## Description Scribe connects your AI agent directly to all your company's process documentation library. It gives your agent access to everything—from formal step-by-step guides (called Scribes) to general knowledge pages. You can ask natural language questions, and your agent pulls answers straight out of the source material. Before you start querying anything, you'll want to verify the connection status; use `check_scribe_status` to make sure your AI client is talking correctly to Scribe's API endpoint. If you need a big picture view, run `get_documentation_stats`. That tool pulls an overview count of every guide, page, and document in the entire system. To see what’s fresh on the books, use `get_recent_documents` to list all content that was created within the last 30 days. When it comes to searching, you've got options depending on how deep you need to dig. If you want your agent to check every single piece of writing—guides and pages combined—you run `search_documents`. But if you know you only care about formal procedures, use `search_scribes` for a targeted query across all dedicated procedural guides. Conversely, if the info is general knowledge, not a step-by-step process, restrict your search to Knowledge Pages using `search_pages`. To filter down how wide that net casts, you can control the scope by team or by date. If you need to know what's only in HR’s docs, first use `list_teams` to get a list of every department configured in Scribe. Once you have that list, your agent narrows the search using `search_by_team`, limiting results just to one specified team. You can also pull all content belonging exclusively to a single team's documentation with `get_team_documents`. If you need to track changes over time, run `search_by_date` to query for documents that fall within a specific date range, using the YYYY-MM-DD format. If your search criteria is hyper-specific—say, only looking at Finance's guides from last quarter—you can combine those searches. For instance, you could use `search_by_team` and then restrict that result set using a date range query. ## Tools ### check_scribe_status Verifies the connection status between your AI agent and Scribe's API endpoint. ### get_documentation_stats Retrieves an overview count of all guides, pages, and documents in the system. ### get_team_documents Fetches all documentation content specifically belonging to one defined team. ### list_teams Returns a list of every distinct department or team configured in your Scribe account. ### search_documents Runs a general query across all Scribe guides and Knowledge Pages combined. ### search_by_date Searches for documents that fall within a specific date range, using YYYY-MM-DD format. ### search_by_team Limits the search scope to only include results from one specified team's documentation. ### search_pages Restricts the search query to only Knowledge Pages, excluding formal step-by-step guides. ### get_recent_documents Lists documents that were created within the last 30 days for immediate review. ### search_scribes Runs a general query across all Scribe's dedicated procedural guides. ## Prompt Examples **Prompt:** ``` Search for all documentation about 'onboarding'. ``` **Response:** ``` Found 12 documents matching 'onboarding': 8 Scribe guides and 4 Knowledge Pages. The most relevant is 'New Employee Onboarding Checklist' (Scribe, HR team). ``` **Prompt:** ``` List all teams in our Scribe organization. ``` **Response:** ``` Your Scribe organization has 5 teams: Engineering (42 docs), Sales (28 docs), HR (19 docs), Marketing (15 docs), and Customer Support (31 docs). ``` **Prompt:** ``` What documents were created in the last 30 days? ``` **Response:** ``` 7 documents were created in the last 30 days: 4 Scribes including 'API Integration Guide' and 'Deployment Checklist', plus 3 Knowledge Pages. ``` ## Capabilities ### Search All Documents Your agent queries every guide and page in the entire Scribe organization simultaneously. ### Filter by Team Scope Your agent limits the search results to documents belonging only to a specified team, like HR or Finance. ### List All Teams Your agent retrieves a list of all teams configured within your Scribe organization for scoping searches. ### Check Document Activity Your agent finds documents created or updated within a specific date range, helping you track recent content additions. ### Audit Documentation Footprint Your agent pulls statistics on the total number of guides and pages stored in your knowledge base. ## Use Cases ### The Support Agent Needs a Guide A customer calls with an obscure billing question. Instead of having the agent run a general `search_documents` query and getting 50 links, you use the agent to scope the search first by running `list_teams` (to confirm the Finance team) and then using `search_by_team`. This narrows results instantly, giving the support agent the one correct step-by-step guide. ### The Operations Lead Needs a Compliance Report Operations needs to verify if all departments have reviewed their onboarding guides. They run `list_teams` first, then loop through each team name and call `get_team_documents`. Finally, they check the total count with `get_documentation_stats`—all without manual clicks. ### Finding a Stale Policy You suspect an old policy document exists but you don't know when it was published. You use `search_by_date` to look at documents created before 2022-01-01, and then run `search_pages` to filter out the formal guides. This helps identify knowledge pages that might be outdated. ### Comparing Guides vs Pages You are writing a new policy but need to see what existing process documentation looks like. You first run `search_scribes` to see the formal, step-by-step guides, and then immediately follow up with `search_pages` to gather background context that isn't tied to a specific workflow. ## Benefits - Audit content gaps quickly. Instead of guessing what docs exist, run `get_documentation_stats` to get a precise count of your entire documentation footprint. - Pinpoint information by department. Use `search_by_team` instead of broad searches when you know the answer lives in the 'Marketing' team's guides. - Stay current on processes. Need to know what changed last week? Run `get_recent_documents` or use `search_by_date` to focus only on new content since the last quarter. - Stop searching everywhere at once. The agent can run multiple queries—for example, first listing teams with `list_teams`, then running a targeted search using `search_scribes` for one of those teams. - Maintain process integrity. By having clear tools like `search_by_team` and `search_documents`, your agents deliver answers that are always scoped correctly, reducing hallucination risk. ## How It Works The bottom line is: you talk to your knowledge base like talking to a person; the server executes complex search logic behind the scenes. 1. Subscribe to this server and provide your Scribe API key (Enterprise Grid or Global plan required). 2. Your AI client sends a natural language query (e.g., 'What's the process for expense reports?') to the MCP Server. 3. The agent runs the appropriate tool (like `search_documents` or `search_by_team`) and returns specific, context-rich answers to your chat window. ## Frequently Asked Questions **How do I check if Scribe is connected to my agent?** You run the `check_scribe_status` tool. It instantly reports whether your API key and connection are active, letting you know right away if you need to re-enter credentials or troubleshoot. **What's the difference between using `search_documents` and `search_scribes`?** `search_documents` is a general query that pulls from all content types (guides, pages, etc.). Use `search_scribes` when you specifically need a formal, step-by-step procedural guide. **How do I find documents written by the Sales team?** Use the `search_by_team` tool and pass 'Sales' as the parameter. This limits your search results only to content generated or managed by that department, making the answer clean and focused. **What if I want to know how much documentation we have?** Run `get_documentation_stats`. This tool gives you a clear count of guides, pages, and total documents. It's fast and gives you a measurable overview of your knowledge base size. **How do I use `list_teams` to map out all the teams in my Scribe organization?** The tool immediately returns a list of every team connected to your Scribe account. This helps you scope your search and understand department document ownership before running specific queries. **What is the correct format for using `search_by_date` to find old documentation?** `Search_by_date` requires dates in YYYY-MM-DD format. You specify a start date and an end date, narrowing your search scope down to that exact window. **When should I use `search_pages` rather than the general `search_documents`?** `Search_pages` limits results strictly to Knowledge Pages. Use this when you know the information is highly structured reference data, not a step-by-step guide. **How do I quickly track documentation activity using `get_recent_documents`?** This tool pulls all documents created within the last 30 days. It's useful for auditing content freshness and identifying which guides need an update or review. **Can I search only for step-by-step guides?** Yes! Use `search_scribes` to search exclusively for Scribe guides, or `search_pages` for Knowledge Pages only. **Do I need an Enterprise plan to use this?** Yes, the Scribe Search & Retrieval API is available on Enterprise Grid and Global plans. Contact Scribe sales for API access. **Can I find documents by a specific team?** Yes! First use `list_teams` to see available teams and their IDs, then use `search_by_team` or `get_team_documents` with the team ID.