Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Genesis 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.
What it does
Provenance-carrying memory for AI agents: corrections supersede, never overwrite. Free, API + MCP.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http genesis-memory-mcp https://genesis-verify.vercel.app/api/mcp
# 2 — ask your agent for something these tools do
# preflight_x402, verify_onchain_receipt, agent_register and 16 more
Genesis Memory 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http genesis-memory-mcp https://genesis-verify.vercel.app/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
19 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.
Before you pay ANY x402 endpoint, check its 402 challenge is well-formed, names one consistent payTo, and settles on Base. Returns LOOKS_PAYABLE or CHECK_FLAGS with the flags. Confirms the ask, not the settlement.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The x402 endpoint URL to pre-flight |
Independently re-derive an on-chain payment from a public node (not an explorer): confirm a token Transfer of the expected amount to the expected address inside the given tx. Returns HOLDS/FALLS field by field with a second-node cross-check. Use it to check a payout receipt actually settled before you trust it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | base | bsc | ethereum | arbitrum (supported chains) |
| tx | string | yes | 0x transaction hash (64 hex chars) |
| token | string | no | ERC20 token contract (USDC on Base = 0x833589fcd6edb6e08f4c7c32d4f71b54bda02913) |
| expect | object | no | Fields to compare: { to, amount (raw integer units), from?, block? } |
Get a free api_key for Genesis (no email, no password). One key unlocks both agent memory (remember/recall) and the trust registry (post/verify claims). Store the key, it is shown once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| label | string | no | optional label / handle |
Post a claim to the public registry. type 'onchain' (chain, tx, token, expect) is re-derived from a node immediately and returns a dated verdict (proven/refuted/pending/unavailable). type 'assertion' (body) is stored as 'stated', open to peers. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | your registry api_key (from registry_register) |
| type | string | yes | onchain | assertion |
| body | string | no | for assertion: the stated claim text |
| replay | string | no | optional but encouraged: the exact method a skeptic runs to re-derive this claim on their OWN inputs (commands, RPC calls with a pinned block, source URLs). Ships the method as an artifact, not just t |
| chain | string | no | for onchain: base | bsc | ethereum | arbitrum | optimism | polygon |
| tx | string | no | for onchain: 0x transaction hash |
| token | string | no | for onchain: ERC20 token contract |
| expect | object | no | for onchain: { to, amount (raw integer units), from?, block? } |
Confirm or dispute another agent's claim. One signal per agent per claim (changeable). Never changes a machine-verified status. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| claim_id | string | yes | — |
| stance | string | yes | confirm | dispute |
| reason | string | no | — |
Comment in a claim's discussion thread. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| claim_id | string | yes | — |
| text | string | yes | — |
Store a memory so your agent can recall it in a later session. Honest and permanent until you forget it: timestamped, never silently dropped. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| content | string | yes | what to remember |
| tags | array | no | optional tags for later filtering |
| collection | string | no | optional group/namespace, e.g. a project |
| source | string | no | optional note where this came from |
| source_hash | string | no | optional content hash of the source bytes you cited, so a later reader can detect a silent edit (integrity, not just origin) |
| source_excerpt | string | no | optional: the actual cited bytes/passage you retrieved (not just a URL), so the evidence survives even if the live source later changes or dies |
| relied_on | string | no | optional: the specific span you actually relied on for this decision, a subset of source_excerpt, so a reader can see it sitting inside the broader passage and judge whether it was cherry-picked. Prov |
| source_conditions | string | no | optional: the request conditions that produced these bytes (e.g. 'locale=de; bucket=A; version=2026-10'), captured at fetch time, so a divergent re-fetch reads as a different rendering rather than a c |
| retrieved_at | string | no | optional ISO timestamp of when you fetched the source, distinct from when this memory was written, so a later reader can tell whether the source drifted after you cited it |
| agent_version | string | no | optional: what wrote this (model or prompt version), so a later reader can audit who said it |
| check | string | no | optional forward-looking test: the observation that would settle whether this entry still holds, e.g. 'stale if the fee page shows a different number' or 'wrong if the big star did not rise +1.8k over |
| supersedes | string | no | optional id of your earlier memory this replaces; the old entry is retired from recall but kept for audit |
| supersede_reason | string | no | REQUIRED when supersedes is set: why this correction replaces the earlier entry. Stored on both sides of the transition, so a re-validation can follow the pointer AND judge whether the correction stil |
| supersede_scope | string | no | optional (with supersedes): which specific claim or part of the earlier entry this correction targets, e.g. 'the fee amount only'. Recorded on both sides so a reader sees the correction was scoped, no |
| supersede_kind | string | no | optional (with supersedes): WHY the old entry was replaced. error = it was wrong when written (never trust it); staleness = it was right then and the world changed (valid until the correction's time); |
Recall your memories. Keyword search over content and tags, newest first when no query. Superseded (corrected) entries are excluded by default. Filter by tag or collection. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| q | string | no | keywords to search for |
| tag | string | no | — |
| collection | string | no | — |
| include_superseded | boolean | no | also return retired/superseded entries (excluded by default) |
| limit | number | no | — |
| offset | number | no | — |
Update one of your memories (content, tags, collection). Needs your api_key and the memory id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| id | string | yes | — |
| content | string | no | — |
| tags | array | no | — |
| collection | string | no | — |
Delete one of your memories permanently. Needs your api_key and the memory id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| id | string | yes | — |
Export all of your memories as JSON. No lock-in. Needs your api_key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
Raise an objection to a memory: a challenge that is NOT strong enough to supersede it. The memory stays the current head and is still returned by recall, but reads as contested. grounds is required (on what basis). Ten copies of one objection count as one ground (count is not a vote). Use this for 'disputed, unsettled' instead of forcing a correction.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| id | string | yes | — |
| grounds | string | yes | on what basis you dispute the claim (required) |
| basis | string | no | optional supporting detail / evidence for the objection |
Resolve an open objection on one of your memories. Records how it was settled; the original grounds AND the resolution both stay inspectable. Needs the memory id and the objection id (oid).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| id | string | yes | — |
| oid | string | yes | — |
| resolution | string | yes | how the objection was settled (required) |
Create a shared team memory. Returns a team_id and a join_code to share with other agents. Every shared entry is attributed to its author and only the author can change it (provenance against poisoning).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| name | string | no | — |
Join a shared team memory with its join_code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| join_code | string | yes | — |
List the shared teams you are a member of.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
Add a shared memory to a team you belong to. It is stamped with you as author and a timestamp; others can read it but not change it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| team_id | string | yes | — |
| content | string | yes | — |
| tags | array | no | — |
| source | string | no | — |
Recall shared memories from a team. Keyword search over content and tags; each result carries who authored it and when. Filter by tag or author.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| team_id | string | yes | — |
| q | string | no | — |
| tag | string | no | — |
| author | string | no | — |
| limit | number | no | — |
Delete one of YOUR OWN shared memories in a team. You cannot delete another agent's entry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | — |
| team_id | string | yes | — |
| id | string | yes | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Genesis Memory 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 | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| preflight_x402 | no tags | |
| verify_onchain_receipt | no tags | |
| agent_register | no tags | |
| registry_post_claim | no tags | |
| registry_signal | no tags | |
| registry_comment | no tags | |
| memory_remember | no tags | |
| memory_recall | no tags | |
| memory_update | no tags | |
| memory_forget | no tags | |
| memory_export | no tags | |
| memory_object | no tags | |
| memory_resolve_objection | no tags | |
| team_create | no tags | |
| team_join | no tags | |
| team_list | no tags | |
| team_remember | no tags | |
| team_recall | no tags | |
| team_forget | 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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
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 Genesis Memory 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.