Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
LoreConvo is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
13
downloads a day
local
runs on your machine
174
downloads in 30d
What it does
Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user loreconvo-mcp '--' uvx loreconvo
# 2 — ask your agent for something these tools do
# save_session, get_recent_sessions, get_session and 38 more
LoreConvo costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts LoreConvo as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user loreconvo-mcp '--' uvx loreconvoReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take LORECONVO_PRO (Pro license key. Leave unset for the free tier.) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
41 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Save a session summary to persistent memory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | Short descriptive title for the session |
| surface | string | yes | Where this session ran - 'cowork', 'code', or 'chat' |
| summary | string | yes | 2-3 paragraph narrative summary of what happened. Capped at 15000 chars. |
| decisions | array | no | List of key decisions made during the session. Each item capped at 2000 chars. |
| artifacts | array | no | List of files created or modified |
| open_questions | array | no | Unresolved questions to carry forward. Each item capped at 2000 chars. |
| tags | array | no | Freeform tags for categorization |
| skills_used | array | no | Skills that were invoked during this session |
| project | string | no | Project name if part of a defined project |
| start_date | string | no | ISO 8601 start time (defaults to now) |
| end_date | string | no | ISO 8601 end time |
| session_id | string | no | Optional session ID to enable deduplication with the auto-save hook. If a session with this ID already exists (e.g., auto-saved at session end), the record is updated with the richer manual metadata. |
| external_tool_session | boolean | no | Set True when saving a session generated by an external tool (e.g., Anthropic Managed Agents). Flagged sessions are excluded from auto-load and search by default to prevent context contamination. Over |
| reasoning_notes | string | no | Optional free-form text capturing the reasoning chain or thought process behind decisions. Blank or None leaves the field empty. Capped at 15000 chars. |
| summarize | boolean | no | If True and ANTHROPIC_API_KEY is set, send the summary to Claude API (Haiku) for compression before saving. Opt-in only; defaults to False. Falls back to the raw summary on any API error or if the key |
Get recent session summaries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Max sessions to return (default 10) |
| days_back | integer | no | How far back to look (default 30 days) |
| project | string | no | Filter to sessions in this project |
| skill | string | no | Filter to sessions that used this skill |
Get full details of a specific session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | The UUID of the session to retrieve |
Search session memory by keyword, with optional filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search keywords (matched against title, summary, decisions) |
| persona | string | no | Filter to sessions tagged with this persona (supports prefix matching) |
| tags | array | no | Filter to sessions with any of these tags |
| skills | array | no | Filter to sessions that used any of these skills |
| project | string | no | Filter to sessions in this project |
| limit | integer | no | Max results (default 10) |
| include_external | boolean | no | If True, include sessions flagged as external_tool_session. Default False. Can also be enabled globally via LORECONVO_EXTERNAL_TOOL_EXCLUSION=0. |
| semantic | boolean | no | If True, use LanceDB hybrid (vector + BM25) search instead of FTS5. Pro tier only. Falls back to FTS5 if index not built yet; run rebuild_index to build it after first Pro activation. |
| include_expired | boolean | no | If True, include sessions whose expires_at is in the past. Default False (expired sessions are hidden from search). |
| after | string | no | Optional ISO 8601 UTC instant (e.g. "2026-07-06T00:00:00Z"). Only sessions started at or after this instant are returned. |
| before | string | no | Optional ISO 8601 UTC instant. Only sessions started strictly before this instant are returned. To answer a question like "what did I work on last week", resolve the range yourself -- you know the use |
Get relevant session context for a topic.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | The topic to find context for (e.g., 'K-1 parser', 'rental insurance') |
| max_results | integer | no | Max excerpts to return (default 5) |
| include_external | boolean | no | If True, include sessions flagged as external_tool_session. Default False. |
| semantic | boolean | no | If True, use LanceDB hybrid search (Pro only). Falls back to FTS5 if index not yet built. |
Store or update a named topic configuration for an agent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_name | string | yes | Canonical agent name (^[a-z][a-z0-9-]{1,63}$). |
| project | string | yes | Project name matching sessions.project (^[a-z_][a-z0-9_]{0,63}$). |
| topics | array | yes | Non-empty list of topic strings; max 10; each max 200 chars. Replaces all existing topics for this (agent_name, project) pair. |
| max_results_per_topic | integer | no | Sessions returned per topic search. 1-10. |
| enabled | boolean | no | Set False to disable injection without deleting the config. |
| retire | boolean | no | Set True to soft-retire this config (status='retired'). inject_agent_context treats a retired config like enabled=0. Any write with retire=False reactivates a previously retired config (reflected in t |
Return targeted session context for an agent at session start.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_name | string | yes | — |
| project | string | yes | — |
| topics | array | no | — |
| max_results_per_topic | integer | no | — |
| semantic | boolean | no | — |
Tag a session with a persona for filtered recall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Session to tag |
| persona_name | string | yes | Persona identifier (e.g., 'ron-bot', 'ron-bot:sql', 'tax-prep') |
| relevance_note | string | no | Optional note about why this session is relevant to the persona |
Link two related sessions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from_id | string | yes | Source session ID |
| to_id | string | yes | Target session ID |
| link_type | string | no | Relationship type - 'continues', 'related', or 'supersedes' |
Find sessions related to a given session by co-occurrence and embedding. Pro only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | UUID of the session to find related sessions for |
| limit | integer | no | Max results to return (default 10, max 50) |
| min_shared_terms | integer | no | Minimum shared keywords required (default 3) |
Render a Mermaid knowledge-graph neighborhood around a session or project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | no | UUID of the seed session. Exactly one of session_id/project required. |
| project | string | no | name of the seed project. Exactly one of session_id/project required. |
| depth | integer | no | number of BFS expansion hops over link edges, clamped [0, 3] |
| max_nodes | integer | no | node budget (sessions + attribute leaves), clamped [1, 200] |
Rebuild the LanceDB semantic search index from all stored sessions. Pro only.
No parameter schema on file.
Get project details including recent sessions and skill usage stats.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_name | string | yes | The project identifier |
List all defined projects with session counts.
No parameter schema on file.
Create or update a project definition.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Project identifier (e.g., 'secret-agent-man', 'project-ron') |
| description | string | no | What this project is about |
| expected_skills | array | no | Skills typically used in this project's sessions |
| default_persona | string | no | Auto-tag new sessions with this persona |
| instructions | string | no | Optional project-wide instructions or constraints |
| session_id | string | no | Optional session ID for audit trail (typically provided by MCP context) |
Set up or update your LoreConvo workspace configuration.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Your workspace or team name (e.g. 'Labyrinth Analytics') |
| projects | array | no | Snake_case project identifiers (e.g. ['side_hustle', 'finance']) |
| agents | array | no | Agent names that will tag sessions (e.g. ['ron', 'meg']) |
| tag_style | string | no | 'simple' (status + priority) or 'detailed' (adds effort, scout-run markers, date tag guidance) |
Get all sessions that used a specific skill.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill_name | string | yes | The skill to look up (e.g., 'rental-property-accounting') |
| days_back | integer | no | How far back to search (default 90 days) |
Get proactive context suggestions based on your session history.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Filter suggestions to this project |
| persona | string | no | Filter to sessions tagged with this persona (prefix matching) |
| days_back | integer | no | How far back to look (default 14 days) |
| limit | integer | no | Max suggestions to return (default 5) |
Return the current LoreConvo license tier and status.
No parameter schema on file.
Activate a tier (free or pro) for LoreConvo.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| params | yes | — |
Export portable session records to JSON or JSONL for migration.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| output_path | string | no | File path to write export (e.g. '/tmp/loreconvo_export.json'). If omitted, data is returned inline. |
| project | string | no | Export only sessions from this project. |
| tags | array | no | Export only sessions that have any of these tags. |
| days_back | integer | no | Limit to sessions from the last N days. Omit for all time. |
| limit | integer | no | Max sessions to export (default 1000). |
| format | string | no | 'json' (array wrapped in metadata) or 'jsonl' (one session per line). |
Export LoreConvo sessions to Anthropic managed-agents memory format. Pro only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| output_path | string | no | File path to write the export. If omitted, data is returned inline. |
| project | string | no | Export only sessions from this project. |
| session_ids | array | no | List of specific session UUIDs to export. Overrides project filter. |
| days_back | integer | no | Limit to sessions from the last N days. |
Import sessions from a LoreConvo export file (JSON or JSONL).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_path | string | yes | Path to the export file (JSON or JSONL format). |
| on_conflict | string | no | What to do if a session ID already exists. 'skip' (default) -- leave the existing session unchanged. 'replace' -- overwrite with the imported version. |
| dry_run | boolean | no | If True, parse and validate the file but make no DB changes. |
Inspect stored sessions: list, filter, or get full detail for one session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | no | If provided, return full detail for this specific session. |
| search | string | no | Full-text search query across title, summary, decisions, tags. |
| tag | string | no | Filter by tag substring (e.g. 'agent:ron', 'side_hustle'). |
| surface | string | no | Filter by surface ('code', 'cowork', 'chat'). |
| since | string | no | Return sessions on or after this date (YYYY-MM-DD). |
| limit | integer | no | Max sessions to return (default 20). |
| show_stats | boolean | no | If True, include aggregate counts (total, by_surface, by_project). |
Return a usage dashboard: session counts by surface, project, and tag;
No parameter schema on file.
Run memory consolidation for a project to build a structured digest.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | yes | Project name (matches the --project tag used when saving sessions) |
| surface | string | no | Surface to consolidate ('code', 'cowork', 'chat', etc.) or None for all |
| max_sessions | integer | no | Maximum number of recent sessions to analyze (default 50) |
| mode | string | no | 'heuristic' (free, default). 'llm' requires Pro (v0.6.1). |
| dedup | string | no | Semantic dedup pass mode: 'off' (default), 'conservative', or 'balanced'. When 'off' (or unset, or unrecognised), the pass does not run and consolidation behaves exactly as before. 'conservative' coll |
Retrieve the current memory digest for a project without re-running consolidation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | yes | Project name |
| surface | string | no | Surface filter (or None for all) |
| disable | boolean | no | If provided, update the disabled flag on the digest |
| max_tokens | integer | no | Truncate digest_markdown to this estimated token limit (len // 4). Default 2000. If truncated, appends [TRUNCATED] marker. |
Set or clear an expiry date on a session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | ID of the session to update |
| expires_at | string | no | ISO 8601 date string (e.g. '2027-01-01T00:00:00Z'), or None to clear |
Return recent consolidation log entries for transparency and diagnostics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Filter by project (or None for all projects) |
| surface | string | no | Filter by surface (or None for all) |
| limit | integer | no | Maximum number of entries to return (default 10, newest first) |
Return LoreDocs documents cross-linked to a LoreConvo session. Pro tier only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
| limit | integer | no | — |
Create a manual cross-product link from a LoreConvo session to a LoreDocs doc.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
| doc_id | string | yes | — |
| vault_id | string | yes | — |
Return MCP compatibility status for this LoreConvo server.
No parameter schema on file.
Retrieve sessions marked as anti-patterns.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Optional keyword to filter within anti-patterns. Omit for all anti-patterns ordered by recency. When provided, uses FTS5 with a fan-out heuristic; result may be truncated if anti-patterns are sparse i |
| limit | integer | no | Max results to return (1-100). Defaults to 10. |
| project | string | no | Restrict to a specific project slug. Case-sensitive. |
Mark an existing session as an anti-pattern. Idempotent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | The sessions.id value to mark (TEXT <= 255 chars). |
| source | string | no | Attribution for this tag (e.g., 'claude-code', 'agent:gina'). |
| reason | string | no | Human-readable reason for the tag. Stored in audit log. |
Remove an anti-pattern tag from a session. Idempotent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | The sessions.id value to untag (TEXT <= 255 chars). |
| source | string | no | Attribution for this untag (e.g., 'claude-code', 'admin'). |
| reason | string | no | Human-readable reason for the removal. Stored in audit log. |
Pin or unpin a session to exclude it from automated cleanup.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
| keep_forever | no | — |
Save a structured memory item: a decision, open question, or artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| item_type | string | yes | One of 'decision', 'open_question', 'artifact'. |
| title | string | yes | The decision text, the question text, or the artifact identifier. Capped at 4096 chars. |
| body | string | no | Free-text detail/rationale for decision/open_question. Ignored for artifacts -- use artifact_type instead. Capped at 4096 chars. |
| session_id | string | no | Originating session, if any. Must reference an existing session. |
| project | string | no | Project namespace (default 'unspecified'). |
| tags | array | no | Freeform tag list. |
| metadata | object | no | Freeform key-value metadata (mainly for artifacts). |
| external_id | string | no | Caller-supplied dedup key, unique per (project, external_id). |
| artifact_type | string | no | For item_type='artifact', the artifact's type (e.g. 'file', 'url'). |
Query structured memory items by type, project, status, and recency.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| item_type | string | no | Filter to 'decision', 'open_question', or 'artifact'. |
| project | string | no | Filter to a project namespace. |
| status | string | no | Filter to a lifecycle status (e.g. 'active', 'open', 'retired'). |
| artifact_type | string | no | Filter artifacts by their artifact_type. Only applies with item_type='artifact'. |
| days | integer | no | Only items created in the last N days. |
| limit | integer | no | Max rows to return (default 50, max 200). |
Move a memory item through its lifecycle.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| item_id | string | yes | The memory item's id. |
| transition | string | yes | 'retire', 'answer', or 'wont-answer'. |
| reason | string | no | Optional free-text reason recorded on close. |
| closing_session_id | string | no | Session performing the transition, if any. Must reference an existing session. |
Correct a memory item's title, body, tags, or metadata, or move it between projects.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| item_id | string | yes | The memory item's id. |
| title | string | no | New title, if changing. |
| body | string | no | New body, if changing. Capped at 4096 chars. |
| tags | array | no | New tag list, if changing (replaces, not merges). |
| metadata | object | no | New metadata dict, if changing (replaces, not merges). |
| new_project | string | no | Destination project, if moving. |
| allow_project_change | boolean | no | Must be True to actually move projects. |
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under BUSL-1.1
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install LoreConvo or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.10.17 · scanned 16 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings11 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest262084effde4f0616051bf4f1bf1e05977bb9813d73a6cd2679763e6f3f8d54f
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (41 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| save_session | state-write | state-write: handler runs a UPDATE statement at src/server.py:296 |
| get_recent_sessions | no tags | |
| get_session | no tags | |
| search_sessions | no tags | |
| get_context_for | no tags | |
| configure_agent_context | no tags | |
| inject_agent_context | no tags | |
| tag_session | no tags | |
| link_sessions | no tags | |
| get_related_sessions | no tags | |
| graph_session_map | no tags | |
| rebuild_index | no tags | |
| rebuild_index_status | no tags | |
| get_project | no tags | |
| list_projects | no tags | |
| create_project | no tags | |
| loreconvo_onboard | no tags | |
| get_skill_history | no tags | |
| vault_suggest | no tags | |
| get_tier | no tags | |
| vault_set_tier | state-write | state-write: declares readOnlyHint: false |
| export_sessions | no tags | |
| export_for_anthropic | no tags | |
| import_sessions | no tags | |
| inspect_sessions | no tags | |
| get_stats | no tags | |
| consolidate_memories | no tags | |
| get_memory_digest | no tags | |
| set_session_expiry | no tags | |
| get_dream_log | no tags | |
| get_docs_for_session | no tags | |
| session_link_doc | no tags | |
| get_server_info | no tags | |
| get_anti_patterns | no tags | |
| tag_as_anti_pattern | no tags | |
| untag_anti_pattern | no tags | |
| pin_session | no tags | |
| save_memory_item | no tags | |
| query_memory_items | no tags | |
| transition_memory_item | no tags | |
| update_memory_item | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest262084effde4f061
Scanned2026-10-16
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.10.17. Pin a release below and the command asks for exactly that one.
0.10.17
15 Oct 2026
latestNo release note was published with this version.
0.10.16
7 Oct 2026
No release note was published with this version.
0.10.15
4 Oct 2026
No release note was published with this version.
0.10.13
3 Oct 2026
No release note was published with this version.
0.10.12
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish LoreConvo can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.