Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Memoria 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.
What it does
Persistent, plain-text memory for agents: markdown you own, hybrid search, self-maintenance.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agripp87-memoria-mcp '--' npx -y @agrippa87/memoria-mcp
# 2 — ask your agent for something these tools do
# memory_search, memory_read, memory_write and 14 more
Memoria costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Memoria 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.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx 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 agripp87-memoria-mcp '--' npx -y @agrippa87/memoria-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take MEMORIA_DIR (Root directory of the memory store. Defaults to ~/.memoria locally (or /data/memoria in Docker).), MEMORIA_EMBEDDINGS (Embedding provider: auto (local MiniLM if installed, else hash; never remote), openai (explicit opt-in: sends content to OpenAI), minilm or hash.) if you want to set them.
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.
17 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Semantic + keyword hybrid search across all memories. Uses three-signal scoring: 0.8·relevance + 0.1·recency + 0.1·importance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query (max 2000 characters) |
| max_results | integer | no | Maximum results to return (1-100) |
Read a specific memory file. Returns empty text (not error) if file doesn't exist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | File path relative to memories/ directory |
| start_line | integer | no | Optional start line (1-based) |
| count | integer | no | Optional number of lines to read |
Create or update a memory file. Checks for similar existing memories before writing (dedup). Returns similar memories if found so the agent can decide: ADD, UPDATE, or NOOP.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | File path relative to memories/ directory (e.g., 'project/new-feature.md') |
| content | string | yes | Full file content including YAML frontmatter |
| force | boolean | no | Skip dedup check and write directly |
List all memory files with their metadata. Optionally filter by type or tag.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by memory type |
| tag | string | no | Filter by tag |
Re-index changed memory files, drop deleted ones, and rebuild the MEMORY_INDEX.md catalog. Use after bulk changes. force=true re-embeds every file even if unchanged (repairs a damaged index).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| force | boolean | no | Re-embed every file, not only changed ones (default false) |
Append an entry to today's daily log (the file is created if it doesn't exist). Use it for what is worth remembering later: decisions made, preferences learned, problems solved, how a piece of work ended. A short summary after substantial work is a good default; routine or trivial sessions don't…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entry | string | yes | The text to append to today's daily log |
Run memory optimization: decay old importance, promote frequent memories, detect stale, find duplicates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | Optimization action to run |
Read recent daily logs and return their content for the agent to synthesize reflections.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | Number of days of daily logs to read (1-365) |
| max_chars | integer | no | Max characters of log content to return, newest first (1-100000) |
Get memory store health metrics: total memories, importance distribution, stale count, access patterns, and health warnings.
No parameter schema on file.
Run proactive health checks: contradiction scan, orphan detection, stale cross-references, missing descriptions, gap analysis. Returns issues for agent review.
No parameter schema on file.
Compile analysis results into a structured core memory. Auto-generates frontmatter, runs dedup check, places file in the correct subdirectory, and updates MEMORY_INDEX.md. Use this to make good query answers persist as permanent knowledge.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | The analysis/answer text to compile into a memory |
| name | string | yes | Short descriptive title |
| type | string | yes | Memory type — determines subdirectory |
| tags | array | yes | Tags for categorization (max 50, each max 100 characters) |
| related | array | no | Related memory file paths (e.g., ['user/profile.md']) (max 50) |
Read the last N days of daily logs and return them grouped + de-duplicated
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | Number of recent daily logs to compact (1-365) |
| max_chars | integer | no | Max characters of output context (1-100000) |
Compile the daily-log firehose into durable, linked entity pages (one
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | How many recent daily logs to roll up |
| min_events | integer | no | Minimum events from a source before it earns a page |
Manage data sources for the sub-memory collector. List available sources, enable/disable them, or add custom sources. User consent for a source can only be granted in the Memoria dashboard, never through this tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | Action to perform |
| source | string | no | Source ID (required for enable/disable/remove/configure) |
| config | object | no | — |
| custom_definition | object | no | Custom source definition (for add_custom) |
Manually trigger ingestion of buffered events into core memory. Useful after enabling a new source or for testing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_size | integer | no | Max events to ingest (1-500) |
| source_filter | string | no | Only ingest events from this source |
Detect patterns across data sources by correlating events within time windows. Creates higher-level activity records.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hours | integer | no | Look back this many hours (1-720) |
| window_minutes | integer | no | Fusion time window in minutes (1-1440) |
View or adjust the priority and filtering settings for the collector daemon. Shows buffer status and active poll timers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | Action to perform |
| source | string | no | Source ID (for set_threshold) |
| threshold | number | no | New importance threshold 1-10 (for set_threshold) |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Memoria or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (17 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| memory_search | no tags | |
| memory_read | no tags | |
| memory_write | no tags | |
| memory_list | no tags | |
| memory_index | no tags | |
| memory_daily | no tags | |
| memory_optimize | no tags | |
| memory_reflect | no tags | |
| memory_stats | no tags | |
| memory_lint | no tags | |
| memory_compile | no tags | |
| memory_compact | no tags | |
| memory_entities | no tags | |
| memory_sources | no tags | |
| memory_ingest | no tags | |
| memory_fuse | no tags | |
| memory_priority | 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
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 0.3.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- 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.
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.
Any signed-in account that does not publish Memoria can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.