Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Feedback Memory 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
5
tools declared
local
runs on your machine
40
downloads
What it does
Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
Quickstart
This one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Publishernot claimed
SPAll 1 server
ssap-pa1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Feedback Memory 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 one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Call this BEFORE you draft anything the user will review (posts, replies, emails, docs, commit messages, UI copy, code in a style they care about). Returns the user's standing rules and their past approve / edit / reject decisions on similar tasks, most similar first. Follow them.
No parameter schema on file.
Call this right AFTER the user approves, edits or rejects something you drafted. Pass the user's reason in one line when they give one: the reason is what makes the next draft better. For an edit, pass the final text the user wanted.
No parameter schema on file.
When the user states a preference that should ALWAYS apply ("never use exclamation marks", "prices only from the database"), save it as a rule. Rules come back first in every recall_corrections.
No parameter schema on file.
Show the active rules, the most recent decisions with their ids, and how many approve / edit / reject decisions were stored in the last 7 days. Use it when the user asks what you remember, or to check that decisions are actually being stored.
No parameter schema on file.
Delete one rule or one stored decision by id (ids come from list_memory). Use when the user says a rule or a past correction no longer applies.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 Feedback Memory 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 0.2.1 · scanned 14 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
Findings3 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digesteb86cb674309d5b40c121086f0510eb451b918ae3349e231338f60c0701e41d2
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 (5 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 |
|---|---|---|
| recall_corrections | external-sink | external-sink: handler sends an HTTP POST (fetch("https://api.openai.com/v1/embeddings") at mcp/server.mjs:35 |
| record_decision | state-writeexternal-sink | state-write: handler runs a INSERT statement at mcp/server.mjs:113; external-sink: handler sends an HTTP POST (fetch("https://api.openai.com/v1/embeddings") at mcp/server.mjs:35 |
| add_rule | state-write | state-write: handler runs a INSERT statement at mcp/server.mjs:130 |
| list_memory | no tags | |
| forget | state-write | state-write: handler runs a DELETE statement at mcp/server.mjs:158 |
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 digesteb86cb674309d5b4
Scanned2026-10-14
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.2.1.
0.2.1
undated
latestNo release note was published with this version.
—
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 Feedback Memory 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.