# io.github.MagneticSnake/genesis-memory

> Provenance-carrying memory for AI agents: corrections supersede, never overwrite. Free, API + MCP.

- name: io.github.MagneticSnake/genesis-memory
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.MagneticSnake%2Fgenesis-memory
- tools: https://api.protogrid.dev/v1/servers/io.github.MagneticSnake%2Fgenesis-memory/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "genesis-memory": {
      "type": "http",
      "url": "https://genesis-verify.vercel.app/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 35
- drivers: +reachable +uptime-100% +updated-1d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: memory_remember (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); team_create (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); preflight_x402 (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,777 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 0 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 19, about 2,777 tokens to load them all
- tool set hash: d9634a1481c8a9f525bebe830ecb37e5
- tools last changed: 2026-10-19T21:00:14.671Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.MagneticSnake/genesis-memory.svg)](https://protogrid.dev/servers/io.github.MagneticSnake/genesis-memory)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `memory_resolve_objection` added
  - 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).
- 2026-10-19 `memory_object` added
  - 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.
- 2026-10-19 `memory_remember` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.MagneticSnake%2Fgenesis-memory/changes

## Remotes

- https://genesis-verify.vercel.app/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (19)

- `agent_register`: 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.
- `memory_export`: Export all of your memories as JSON. No lock-in. Needs your api_key.
- `memory_forget`: Delete one of your memories permanently. Needs your api_key and the memory id.
- `memory_object`: 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.
- `memory_recall`: 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.
- `memory_remember`: 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.
- `memory_resolve_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).
- `memory_update`: Update one of your memories (content, tags, collection). Needs your api_key and the memory id.
- `preflight_x402`: 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.
- `registry_comment`: Comment in a claim's discussion thread. Needs your api_key.
- `registry_post_claim`: 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.
- `registry_signal`: Confirm or dispute another agent's claim. One signal per agent per claim (changeable). Never changes a machine-verified status. Needs your api_key.
- `team_create`: 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).
- `team_forget`: Delete one of YOUR OWN shared memories in a team. You cannot delete another agent's entry.
- `team_join`: Join a shared team memory with its join_code.
- `team_list`: List the shared teams you are a member of.
- `team_recall`: 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.
- `team_remember`: 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.
- `verify_onchain_receipt`: 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.