Skip to main content
MCP Server

Shared Context & Knowledge

pf-context

The shared read layer.

A work in progress
We've published these resources in the hope they're useful — you're welcome to copy or use anything you find on this site. We're still working through each record to optimise it for completeness and accuracy, so some entries are fuller than others for now.

What it does

The shared read layer. It gives every agent one consistent way to look up the knowledge base, the agent registry, the design system, the product catalogue, forms, personas, and published content — so nobody has to re-derive what is already known.

Tools it exposes

Connects to Internal Tools + Public Pages databases (read-only). Each tool below is a single, well-defined capability — described in plain language.

  • List_Brain_CategoriesBrowse the fixed set of knowledge-base categories.Connects to: brain.categories
  • List_Brain_EntriesBrowse knowledge entries, optionally filtered by category or slug.Connects to: brain.entries
  • Get_Brain_EntryRead the full content of a single knowledge entry.Connects to: brain.entries
  • List_Load_RulesSee which knowledge a given task keyword should load.Connects to: brain.load_rules
  • Get_Load_RuleLook up the required and optional knowledge for one task keyword.Connects to: brain.load_rules
  • Resolve_ContextFetch all the knowledge an agent needs for a task in a single call.Connects to: brain (knowledge base)
  • List_AgentsView the roster of every specialist agent.Connects to: brain.agents
  • Get_AgentRead one agent's full directory record.Connects to: brain.agents
  • List_PersonasFetch the full cast of animal personas, ready for composition.Connects to: social_animal_personas
  • Get_PersonaGet one animal persona by name.Connects to: social_animal_personas
  • List_Design_TokensBrowse the design system's colour, type, spacing, and motion values.Connects to: design.tokens
  • Get_Design_TokenRead the full details of a single design token.Connects to: design.tokens
  • List_Design_ComponentsBrowse the catalogue of UI components.Connects to: design.components
  • Get_Design_ComponentFetch a component and its ready-to-use HTML and CSS variants.Connects to: design.components + variants
  • List_Motion_PresetsDiscover the named animation recipes.Connects to: design.motion_presets
  • Get_Motion_PresetRead the full specification for one animation preset.Connects to: design.motion_presets
  • List_Revenue_ProductsBrowse the catalogue of one-time products.Connects to: revenue.products
  • Get_Revenue_ProductRead a product's full details and pricing.Connects to: revenue.products
  • List_Payment_PlansView the recurring subscription plans.Connects to: revenue.payment_plans
  • Get_Payment_PlanRead a plan's pricing, discounts, and attached add-ons.Connects to: revenue plans + add-ons
  • List_AddonsDiscover the add-ons that can attach to plans.Connects to: revenue.addons
  • List_FormsBrowse form definitions.Connects to: forms.definitions
  • Get_FormRead a form's full definition, fields, and routing.Connects to: forms.definitions
  • List_Field_TypesSee every supported form field type.Connects to: forms.field_types
  • List_Blog_PostsBrowse published articles, newest first.Connects to: blog_posts
  • Get_Blog_PostRead a full published article with its content and SEO.Connects to: blog_posts
  • List_Blog_CategoriesDiscover the article categories.Connects to: blog_categories
  • List_FAQView the visible FAQ entries.Connects to: public.faq

Built and maintained by the MCP agent

This server was built with FastMCP and Python by our MCP agent, to spec. In practice it takes well under thirty minutes of hands-on direction — agents are genuinely good at building these. The value is in the design: each server exposes only the endpoints we want, with clear descriptions and parameters tuned to our goals.

Meet the MCP agent

You don't need all of this to start

Most of what these agents rely on has a simpler equivalent. Anywhere we use a database, you can usually start with a spreadsheet or a document — whatever you're comfortable with. Anywhere we built a custom MCP server, you can reach for a prebuilt AI connector instead of building your own.

We go further because it's where our experience pays off. Years of hands-on database work make a custom data layer feasible for us, and purpose-built MCP servers let us hand each agent a short, sharp instruction file and exactly the tools it needs — custom descriptions, only the endpoints we want, and the occasional extra gate — instead of a long manifesto or playbook. Nothing more, nothing less.

Ready to build technology that works for your mission?

Tell us where your organisation is and what's slowing your team down. We respond personally.

FAQ — Knowledge Base

Browse frequently asked questions about Knowledge Base

Request an Invitation to the MMP

Mission Multiplier cohorts form on a rolling basis. Request an invitation and we'll reach out when a cohort that fits you is coming together. No payment until you're invited and confirm your spot.