MCP Tools Reference

All 9 Lore MCP tools with parameters, descriptions, and usage examples.

Lore exposes 9 tools via MCP. They fall into three categories: simple query tools (fast, cheap), agentic tools (multi-step, higher cost), and management tools.

search

Semantic search across the knowledge base. Returns source summaries with relevance scores.

Parameter	Type	Required	Description
`query`	string	Yes	Search query
`project`	string	No	Filter to specific project
`source_type`	string	No	Filter by source type (e.g. "meeting", "slack")
`content_type`	enum	No	Filter by content type (interview, meeting, conversation, document, note, analysis)
`limit`	number	No	Max results (default 10)
`include_archived`	boolean	No	Include archived projects (default false)
`mode`	enum	No	Search mode: hybrid (default), semantic, keyword, regex

Search modes:

hybrid (default) — Combines vector similarity + full-text search via RRF fusion. Best for most queries.
semantic — Vector similarity only. Use for conceptual queries where exact terms don't matter.
keyword — Full-text search only. Use for exact terms, identifiers, or proper nouns.
regex — Pattern matching in local files.

get_source

Retrieve full details of a source document by ID.

Parameter	Type	Required	Description
`source_id`	string	Yes	ID of the source document
`include_content`	boolean	No	Include full original content (default false)

Use after search returns a relevant source_id and you need the full document.

list_sources

Browse all sources, optionally filtered by project or type.

Parameter	Type	Required	Description
`project`	string	No	Filter to specific project
`source_type`	string	No	Filter by source type
`limit`	number	No	Max results (default 20)

list_projects

List all projects with source counts and latest activity dates. Takes no parameters.

ingest

Push content into the knowledge base. Handles both full documents and short insights/decisions. This is how AI agents save knowledge from conversations — users can simply ask their AI to "save this to lore" or "remember this decision."

Parameter	Type	Required	Description
`content`	string	Yes	Document content
`title`	string	No	Title (auto-generated from content if not provided)
`project`	string	Yes	Project this belongs to
`source_type`	string	No	Content category (meeting, slack, github-issue, etc.). Defaults to "document"
`date`	string	No	ISO date (defaults to now)
`participants`	string[]	No	People involved
`tags`	string[]	No	Tags for categorization
`source_url`	string	No	Original URL for citation linking
`source_name`	string	No	Human-readable origin label

Idempotent — content is deduplicated by SHA256 hash. Safe to call repeatedly.

Short content (≤500 chars) skips LLM extraction for speed — the content itself is used as the summary.

Natural language examples (what you'd say to your AI):

"Save this architecture decision to lore under the backend project"
"Ingest these meeting notes — project is product, participants are Sarah and Mike"
"Remember that we chose JWT over sessions for mobile compatibility"

research

Start a comprehensive research job. An internal agent iteratively searches, reads sources, cross-references findings, and synthesizes a research package with citations.

Parameter	Type	Required	Description
`task`	string	Yes	Research task description
`project`	string	No	Focus research on specific project
`include_sources`	boolean	No	Include source references (default true)

Async: Returns immediately with a job_id. Poll research_status to get results. Research typically takes 2-8 minutes.

Cost: Makes multiple LLM calls internally (typically 10-30 cycles). Use search for simple lookups.

research_status

Poll for research job results. Long-polls for up to 20 seconds before returning.

Parameter	Type	Required	Description
`job_id`	string	Yes	The job_id returned by `research`

Returns an activity array showing what the agent is doing (searches, sources read, reasoning). When status is "complete", the full research package is in result.

sync

Sync from configured source directories.

Parameter	Type	Required	Description
`git_pull`	boolean	No	Pull from git remote (default true)
`git_push`	boolean	No	Push to git remote (default true)
`index_new`	boolean	No	Index new sources found (default true)
`dry_run`	boolean	No	Preview only (default false)

archive_project

Archive a project, excluding it from default search.

Parameter	Type	Required	Description
`project`	string	Yes	Project name to archive
`reason`	string	No	Why it's being archived
`successor_project`	string	No	Replacement project, if any