> ## Documentation Index
> Fetch the complete documentation index at: https://docs.baselayer.id/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Tools Overview

> All eleven BaseLayer MCP tools at a glance.

# MCP Tools Overview

BaseLayer exposes eleven tools via MCP. Any connected AI can call these to interact with your memory.

## Querying

| Tool                               | Purpose                           | When to use                                                          |
| ---------------------------------- | --------------------------------- | -------------------------------------------------------------------- |
| [ask\_question](/api/ask-question) | Synthesize answers with citations | Factual questions about you, your projects, preferences, and history |

## Searching & Exploring

| Tool                                                  | Purpose                                   | When to use                                                  |
| ----------------------------------------------------- | ----------------------------------------- | ------------------------------------------------------------ |
| [memory\_search](/api/memory-search)                  | Semantic search across entities and facts | Browsing, exploring, or discovering entities in your memory  |
| [get\_entity](/api/get-entity)                        | Fetch a full entity dossier               | Deep dive into a specific person, project, plan, or concept  |
| [get\_entity\_relations](/api/get-entity-relations)   | Browse graph edges and connections        | Understanding how entities are linked, filtering connections |
| [get\_entity\_provenance](/api/get-entity-provenance) | Track fact origins                        | Verifying where knowledge came from, auditing sources        |
| [list\_entities](/api/list-entities)                  | Browse all entities of a type             | Discovering what's in your memory, finding plans             |
| [recent\_conversations](/api/recent-conversations)    | Load recent dialogue context              | Start of a conversation, catching up on recent activity      |
| [retrieve\_evidence](/api/retrieve-evidence)          | Search raw conversation windows           | Finding exact quotes, code snippets, or original wording     |

## Writing

| Tool                                 | Purpose                           | When to use                                       |
| ------------------------------------ | --------------------------------- | ------------------------------------------------- |
| [record\_memory](/api/record-memory) | Persist observations and context  | Saving decisions, notes, corrections, preferences |
| [vault\_fact](/api/vault-fact)       | Assert precise facts in the graph | Creating specific entity relationships and edges  |
| [update\_plan](/api/update-plan)     | Persistent markdown scratchpads   | Tracking multi-step efforts across sessions       |

## Common patterns

**Start of conversation:** The AI calls `recent_conversations` to load recent context, then uses `ask_question` as needed throughout the conversation.

**Factual questions:** `ask_question` first for a synthesized answer with citations, then `get_entity` if more detail is needed on a specific entity.

**Research mode:** `memory_search` to discover entities, then `get_entity` for full dossiers, then `get_entity_relations` to explore connections.

**Storing knowledge:** `record_memory` for general notes and decisions, `vault_fact` for precise facts linking two entities.

**Plans:** `update_plan` to create or update a persistent scratchpad, `get_entity(type="plan")` to read it back in any future session.

## Tool priority order

When an AI needs to find information, it should follow this priority chain:

1. **ask\_question** -- always try this first for any factual query
2. **memory\_search** -- browse, explore, or find entities by type
3. **get\_entity** -- read a full dossier before acting on partial search results
4. **retrieve\_evidence** -- only when exact quotes or raw context are needed

## How AIs use these tools

You don't need to explicitly ask your AI to call these tools. Connected AIs use them naturally based on context:

* If you ask about past work, the AI calls `ask_question`
* If you share a decision, the AI calls `record_memory`
* If you ask "what do you know about X," the AI calls `get_entity`
* If you start a multi-session effort, the AI creates a plan with `update_plan`

You can also explicitly request tool calls:

> "Search my memory for anything about the Stripe integration."

> "Remember that we decided to use Redis for caching."

> "Create a plan to track the auth refactor."