Lore Context

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

Connector by Lore-Context · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 4

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lore-context-lore-context-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 16 read · 8 write · 1 delete · 9 not yet classified
Secrets: 1 (API keys, tokens or passwords)
Install scripts: Not scanned yet
Runs as: Node.js package

Tools by what they do 34

Read from the source code; the running server may list different tools.

Read 16 · Look things up without changing anything.

code.list_repos
code.search
code.search_text
evidence.trace_get
memory_get
memory_list
memory_search
memory.inbox_list
memory.recall
memory.suggest
profile.get
repo.detect_changes

Show 4 more tools

repo.graph_query
repo.impact
repo.symbol_context
trace_get

Write 8 · Create, change, send or run things.

eval_run
memory_supersede
memory_update
memory_write
memory.add_candidate
memory.inbox_approve
memory.inbox_reject
profile.update_candidate

Delete 1 · Delete, drop, revoke or wipe things.

memory.delete

Not yet classified 9 · We could not tell from the name and description.

code.callgraph
code.context
code.impact
code.references
context_query
memory_export
memory_forget
source.pause
source.resume

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

LORE_API_KEY

Other settings (environment variables or headers).

LORE_API_URL
LORE_MCP_TRANSPORT

Files it touches

Any path the agent passes to its tools

Tools (34)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

code.callgraph
BFS call-chain subgraph from a given symbol up to the requested depth (1-5). Returns nodes and edges.
code.context
Given a fully-qualified symbol name, returns the symbol metadata plus all incoming references (callers/importers) and outgoing references (callees/imports).
code.impact
Blast-radius analysis: transitive closure of code.references up to depth N. Hard cap of 500 symbols with pagination cursor. code.impact(X, depth=∞) is algorithmically identical to BFS closure of code.references(X).
code.list_repos
List all code repos indexed in the current vault. The last_indexed_at field is the staleness signal — compute staleness locally as Date.now() - last_indexed_at.
code.references
Reverse-index lookup: all symbols in the vault that reference the given target symbol. Same shape as incoming[] from code.context but exposed as a top-level tool.
code.search
Hybrid BM25 + dense-embedding search over all indexed code symbols in the current vault. Returns top-K matches with file paths, line ranges, and relevance score.
code.search_text
Regex/grep search over symbol name and doc_comment columns only (NOT function bodies — bodies are never stored). Uses Postgres ~ operator.
context_query
Compose governed, agent-ready context for a user query from memory, web, repo evidence, and tool traces. Use this as the default read path before answering from Lore memory.
eval_run
Run retrieval evaluation over uploaded sessions or a v12/v13 recipe dataset.
evidence.trace_get
Read an Evidence Ledger for a context trace id.
memory_export
Export visible memories as Lore JSON or Markdown.
memory_forget
Forget memories by explicit selector. Requires a reason and defaults to soft delete.
memory_get
Read one visible Lore memory by id.
memory_list
List visible memories with pagination and filters.
memory_search
Search visible Lore memories directly.

Show 19 more tools

memory_supersede
Create a new version of a memory and mark the previous one superseded.
memory_update
Edit an existing memory. Risky content returns to the governance review queue.
memory_write
Save a user-approved or project-relevant memory with audit logging.
memory.add_candidate
Add a beta memory candidate through governed memory writeback.
memory.delete
Delete memories by explicit selector. Requires a reason and defaults to soft delete.
memory.inbox_approve
Approve a memory candidate from the governance review queue.
memory.inbox_list
List memory candidates currently waiting for governance review.
memory.inbox_reject
Reject a memory candidate from the governance review queue. Requires a reason.
memory.recall
Hosted MCP recall entrypoint. Composes governed, agent-ready context and returns its trace id for audit.
memory.suggest
Given a user message in context, returns the top-K canonical memories the host should consider injecting into the system prompt or message prefix before LLM inference. This is a recommendation, not a mutation — the host decides whether to use the suggestions. Routes through canonical_index fast-path first; falls through to 7-stream hybrid search if no canonical hit. Token budget is enforced via tiktoken cl100k_base approximation (±10% drift for non-GPT models).
profile.get
Read the beta profile contract when the profile API is available.
profile.update_candidate
Submit a beta profile update candidate when the profile API is available.
repo.detect_changes
Map a unified diff to indexed files/symbols and return affected upstream symbols and suggested tests from Lore's repo graph.
repo.graph_query
Query Lore's repository knowledge graph for files, symbols, and relations. Use this as the repo-native replacement for external code graph lookup.
repo.impact
Analyze blast radius for an indexed symbol or file using reverse repo graph traversal. Returns callers, upstream affected symbols, and suggested tests.
repo.symbol_context
Return a symbol definition with incoming callers/references, outgoing callees/imports, related tests, and process placeholders from Lore's repo graph.
source.pause
Pause a hosted capture source by writing a paused heartbeat.
source.resume
Resume a hosted capture source by writing an active heartbeat.
trace_get
Read a context or memory trace by id.

Signals

Stars: 4
Forks: 1
Open issues: 0
Weekly downloads: 14
Last commit: May 23, 2026 (5 months ago)
Last release: Apr 29, 2026 (6 months ago)
Last package publish: Apr 29, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.Lore-Context/lore-context-mcp
Version: 0.6.0-alpha.1
Auth: API key
Packages: npm @lore-context/serveroci ghcr.io/lore-context/lore-context-mcp:0.6.0-alpha.1
License: Apache-2.0
Repository: github.com/Lore-Context/lore-context
Website: lorecontext.com
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

Cite this page

Lore Context MCP server. Agent Mart. https://agentmart.dev/connectors/lore-context-lore-context-mcp (last updated 2026-10-24)