RE-call MCP Memory Server runs on your own machine — the client starts it, so there is no endpoint to ping. 79 installs a week from pypi. Last commit 1 Nov 2026.
Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.
What the code does
We read the source, 14 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
done = subprocess.run(
_ACTIVE_GENERATION_SELECT + _ACTIVE_GENERATION_TENANT[bool(tenant)],
root = next((path for path in staging.iterdir() if path.is_dir()), staging)
values = env if env is not None else dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add re-call -e 'RECALL_SERVING_DSN=<RECALL_SERVING_DSN>' -- uvx recall-rag{
"mcpServers": {
"re-call": {
"command": "uvx",
"args": [
"recall-rag"
],
"env": {
"RECALL_SERVING_DSN": "<RECALL_SERVING_DSN>"
}
}
}
}[mcp_servers.re-call]
command = "uvx"
args = ["recall-rag"]
env = { RECALL_SERVING_DSN = "<RECALL_SERVING_DSN>" }{
"mcpServers": {
"re-call": {
"command": "uvx",
"args": [
"recall-rag"
],
"env": {
"RECALL_SERVING_DSN": "<RECALL_SERVING_DSN>"
}
}
}
}{
"servers": {
"re-call": {
"type": "stdio",
"command": "uvx",
"args": [
"recall-rag"
],
"env": {
"RECALL_SERVING_DSN": "<RECALL_SERVING_DSN>"
}
}
}
}Put your own value in place of
<RECALL_SERVING_DSN> (PostgreSQL serving DSN for the RE-call memory store).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
RECALL_TENANT (Tenant id served by this local stdio server), RECALL_TRUST_MODE (Set to development only for local uncalibrated corpora), RECALL_EMBEDDER (The embedder the corpus was BUILT with, for example voyage:voyage-4 or BAAI/bge-large-en-v1.5. It must match: several models emit 1024 dimensions, so a mismatch does not error, it returns a confidently ranked list that means nothing), RECALL_TABLE (The chunk table inside that database. `recall quickstart` indexes into quickstart_chunks so its sample corpus can never be retrieved beside real memory; `recall setup` uses chunks. The wrong value returns no hits and no error), RECALL_MCP_TOOLS (Optional. Serve a subset of the tools: a preset (all, search, read) or explicit names. Every tool definition is re-sent every turn, so serving ones nobody calls costs input tokens on every turn. Unset serves them all).
Alternatives to RE-call MCP Memory Server
same job, measured the same wayShared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Give your agent its own cloud: Postgres, Redis, a sandbox or any Docker image, in one MCP call.
Versioned agent memory in your own Postgres: portable context, permissioned, audit trail.
MCP server giving AI agents persistent SQLite memory that proves which lessons hold.
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Agent memory that keeps every correction, with history and as-of reads. Runs on your database.
RE-call MCP Memory Server — questions
Answers built from our own checks of this server.