Search / io.github.mifactory-bot/mifactory-agent-memory
mifactory-agent-memory
R0· no sign-inPersistent memory for AI agents across Claude, ChatGPT and any MCP client.
v1.3.1 · active · repository · descriptor JSON · versions
Search / io.github.mifactory-bot/mifactory-agent-memory
R0· no sign-inPersistent memory for AI agents across Claude, ChatGPT and any MCP client.
v1.3.1 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"mifactory-agent-memory": {
"type": "http",
"url": "https://agent-memory-api.vercel.app/mcp"
}
}
}claude mcp add --transport http mifactory-agent-memory https://agent-memory-api.vercel.app/mcp[mcp_servers.mifactory-agent-memory]
url = "https://agent-memory-api.vercel.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mifactory-agent-memory": {
"type": "remote",
"url": "https://agent-memory-api.vercel.app/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"mifactory-agent-memory": {
"type": "http",
"url": "https://agent-memory-api.vercel.app/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mifactory-agent-memory&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnQtbWVtb3J5LWFwaS52ZXJjZWwuYXBwL21jcCJ9"
}{
"servers": {
"mifactory-agent-memory": {
"type": "http",
"url": "https://agent-memory-api.vercel.app/mcp"
}
}
}{
"mcpServers": {
"mifactory-agent-memory": {
"httpUrl": "https://agent-memory-api.vercel.app/mcp"
}
}
}extensions:
"mifactory-agent-memory":
enabled: true
name: "mifactory-agent-memory"
type: streamable_http
uri: "https://agent-memory-api.vercel.app/mcp"
timeout: 300
protocol.modernnewest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: memory_read (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_write (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)tools.token_costabout 80 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changesno tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +reachable +uptime-100% -stale-192d
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://agent-memory-api.vercel.app/mcp streamable-http | none | yes | 100% | 235 ms | 2024-11-05 | 2026-10-20 |
memory_read | Read from agent memory |
memory_write | Write to agent memory |
Schemas: list_tools.
And 1 more from this publisher.
{
"name": "io.github.mifactory-bot/mifactory-agent-memory",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://agent-memory-api.vercel.app/mcp",
"type": "streamable-http"
}
],
"version": "1.3.1",
"repository": {
"url": "https://github.com/mifactory-bot/agent-memory-api",
"source": "github"
},
"description": "Persistent memory for AI agents across Claude, ChatGPT and any MCP client."
}