update_knowledge

MCP tool from Piia Engram by Patdolitse

Update a lesson or decision by ID

How to use it

update_knowledge is exposed by the Piia Engram MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the update_knowledge tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Piia Engram

$claude mcp add piia-engram -- piia-engram-mcp

FULL PIIA ENGRAM LISTING

Other tools in Piia Engram (39)

add_decision

Record a key decision with reasoning

add_lesson

Store a reusable lesson learned

add_playbook

Record an operational playbook (multi-step procedure with trigger keywords)

archive_knowledge

Archive a lesson or decision by ID

confirm_knowledge

Owner-only confirmation stamp via human, test, or anchor provenance

doctor

Run memory system self-diagnosis

extract_session_insights

Extract lessons and decisions from session text

find_tool

Optional local integration: look up a registered local tool by name

get_daily_log

Read a human-friendly project timeline for a day

get_decisions

List key decisions; threadseedid / historyquestion reconstruct decision threads and revision history

get_identity_card

Owner-gated export: write and return a Markdown identity card for non-MCP tools

get_identity_facets

Read identity facets via facet: profile, preferences, trustboundaries, workstyle, qualitystandards, domains, or all

get_knowledge_inheritance

Build cross-project knowledge starter pack

get_lessons

List reusable lessons learned

get_playbooks

Playbook reads via mode: list, get (full content), recent, management (incl. archived/deleted metadata)

get_project_context

Read a saved project snapshot

get_recall

Return one structured identity + recent activity + relevant knowledge recall payload

get_recent_context

Recover lost session context after restart

get_relevant_knowledge

Find knowledge relevant to current project

get_resume_brief

Build a cross-session/cross-tool resume brief

get_user_context

Startup — Load identity + knowledge at session start (supports tokenbudget for context size control)

ingest_notes

Parse free-form notes into structured knowledge

list_agent_sessions

Browse saved session records across tools

list_projects

List saved project snapshots

list_tools

Optional local integration: list registered local tools (optionally filter by category)

manage_playbook

Playbook lifecycle via action: update, archive, delete, restore (mutations stay confirm-gated)

memory_store

Writeback — Unified write endpoint: routes to addlesson / adddecision / addplaybook by kind

onboard_repo

Owner-only repo scan: create staging repo-fact candidates from anchors

OpenClaw

SOUL.md / MEMORY.md / USER.md import and export

playbook_execution

Guided execution via action: prepare a step plan, updatestep, status rollup (passive reference; no auto-execution)

preview_context_governance

Advanced owner-gated preview: build safe-context, freshness/conflict, replay, or evidence proposals without applying changes

refresh_quick_context

Refresh local quickcontext.md snapshot for offline/cross-tool use

register_tool

Optional local integration governed write: register a local tool, runtime, or CLI to the environment map

save_agent_context

Save AI session checkpoint (also runs automatically)

save_project_snapshot

Persist project state for future sessions

search_knowledge

Retrieval — Search lessons, decisions, and playbooks (supports filtersjson for domain/tier/date filtering)

update_identity

Update profile, preferences, or quality standards

user_portrait

action: get / save / compare the AI-maintained user portrait

wrap_up_session

Session end — Save insights + sync at session end