Agentram Mcp

io.github.seanmarkweiPublished by GitHub account seanmarkweiv0.1.1Updated Oct 24, 2026

Model Context Protocol server for AgentRAM. Persistent memory for AI agents.

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

AgentRAM MCP gives an AI assistant persistent memory through a hosted HTTP memory store, with flat key-value memories, shared namespaces and temporal assertions

What you can do
Save, read, list, text-search and delete flat key-value memories for an agent, and check the credit balance of the account. Create shared namespaces and store, read and list memories in them so several agents can use one pool. Record temporal assertions for facts that change, retire them while keeping history, and read the current value, all current facts or the full history of a key. Contested keys are reported with both values instead of a silent winner.
When to use it
Use it when an assistant should remember information across sessions without running a vector database or embedding pipeline, or when several agents need a shared memory pool and you want a history of facts that change over time.
Requirements
A local Node.js runtime (Node 18 or newer) to run the npm package through npx, plus an AgentRAM account and API key supplied in the AGENTRAM_API_KEY environment variable. Network access to the AgentRAM API; the base URL can be overridden with AGENTRAM_API_BASE.
Before you install
The API key is a secret passed in AGENTRAM_API_KEY and should not be shared. Stored memories are sent to the AgentRAM hosted service, so avoid putting sensitive data in them. Tools can write, overwrite and delete memories, and new accounts start with a limited credit balance that calls may consume.

Installation

In SourceWeft

  1. Open Agentram Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentram-mcp

MCP server for AgentRAM. It gives your AI agents persistent memory through a set of tools, with no vector database and no embedding pipeline to set up. Get a key, paste the config below, and you're running in about a minute.

Works with any MCP client: Claude Desktop, Claude Code, Cline, Cursor, Windsurf, and others.

Why

Every agent session starts with amnesia. AgentRAM is a plain HTTP memory store built for agents: one call to save something, one call to read it back. No infra to stand up, no vectors to babysit. This package wraps that API as MCP tools so your agent can just use it.

Setup

You need an API key first. Register at agentram.dev and it gets emailed to you. New accounts start with 1,000 credits and no card is required.

Then add this to your client's MCP config. For Claude Desktop that file is claude_desktop_config.json (on macOS it lives at ~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "agentram": {      "command": "npx",      "args": ["-y", "agentram-mcp"],      "env": {        "AGENTRAM_API_KEY": "agentram_your_key_here"      }    }  }}

Restart the client and the tools show up. Most clients let you mark them "always allow" so you're not clicking approve on every call.

One gotcha on macOS: Claude Desktop doesn't ship with Node, so install Node 18 or newer first or the server won't start.

Tools

Fifteen tools. Ten for flat memory, five for temporal memory (facts that change over time).

Flat memory:

  • store_memory: save a value under a key for an agent
  • retrieve_memory: read one back by key
  • list_memories: list everything stored for an agent
  • search_memories: text search across keys and values, no embeddings needed
  • delete_memory: remove one
  • check_credits: current balance, free to call

Shared memory, for when more than one agent needs the same pool:

  • create_namespace: make a shared space, free to call
  • store_shared_memory: write into it
  • retrieve_shared_memory: read from it
  • list_shared_memories: list what's in it

Temporal memory (assertions):

  • store_assertion: record a fact that can change, like a plan, a status, or a preference
  • retire_assertion: mark a fact as no longer true while keeping the history
  • get_assertion: what's currently true for a key
  • list_assertions: all the current facts for an agent
  • get_assertion_history: the full chain of what a key has been over time

About temporal memory

Flat memory overwrites. Temporal memory keeps the trail. When a fact changes you supersede the old value, and the previous values stick around so you can see how you got to the current one.

The part worth knowing: if two different values land on the same key and neither one supersedes the other, get_assertion will not quietly pick a winner. It tells you the key is contested and returns both values, so your agent can decide instead of running on a guess. list_assertions flags which keys are in that state.

Flat and temporal are separate keyspaces. A key called plan in store_memory and a key called plan in store_assertion have nothing to do with each other. Use flat memory for stuff you just overwrite, and assertions for facts you want a record of.

Credits

Reads and writes cost 1 credit each. check_credits and create_namespace are free. A read that finds nothing (a 404) refunds the credit. Most responses include your credits_remaining so you can watch the balance.

Config

  • AGENTRAM_API_KEY (required): your key, starts with agentram_
  • AGENTRAM_API_BASE (optional): defaults to https://api.agentram.dev

Links

MIT

Source: README.md at commit 3e88b5e

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts