Skip to content
Agentmart
Submit a tool

Agentram MCP

Model Context Protocol server for AgentRAM.

Connector by seanmarkwei · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Chalk Labs

Need help deploying Agentram MCP?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/seanmarkwei-agentram-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
9 read · 5 write · 1 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 15

Read from the source code; the running server may list different tools.

Read 9 · Look things up without changing anything.

  • check_credits
  • get_assertion
  • get_assertion_history
  • list_assertions
  • list_memories
  • list_shared_memories
  • retrieve_memory
  • retrieve_shared_memory
  • search_memories

Write 5 · Create, change, send or run things.

  • create_namespace
  • retire_assertion
  • store_assertion
  • store_memory
  • store_shared_memory

Delete 1 · Delete, drop, revoke or wipe things.

  • delete_memory

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • AGENTRAM_API_KEY

Tools (15)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_credits

    Return the current credit balance for your account. Free to call (no credit deducted).

  • create_namespace

    Create a shared memory namespace that multiple agents can read from and write to. Returns a namespace_key to share with each agent. Free to call (no credit deducted).

  • delete_memory

    Permanently delete a stored memory. Cannot be undone. Costs 1 credit.

  • get_assertion

    Return what is currently true for an agent_id and key. IMPORTANT: if the key is contested (two or more live values with neither superseding the other), this returns ALL competing values and flags the conflict rather than silently choosing one — surfacing conflicts is the point. Returns nothing (404, credit refunded) if the key was never set or has been retired. A contested read is charged. Costs 1 credit.

  • get_assertion_history

    Return the full chain of values a key has held over time, newest first — each value, who wrote it, and which earlier assertion it superseded. Answers 'why does the agent still believe X?' and audits how a fact evolved. Bounded: returns a truncated flag when more exist. Costs 1 credit.

  • list_assertions

    List every currently-true fact for an agent_id, one entry per key. Contested keys are flagged so you know which facts are in conflict; resolve one with get_assertion on that key, then store_assertion with its assertion_id in `supersedes`. Retired and expired keys are excluded. Costs 1 credit.

  • list_memories

    List all memories stored under an agent ID, ordered by most recently written. Expired memories are excluded. Costs 1 credit.

  • list_shared_memories

    List all memories in a shared namespace, ordered by most recent. Costs 1 credit.

  • retire_assertion

    Mark a fact as no longer true, with no replacement value. Appends a tombstone: the fact stops being returned as current but stays in the history. Use when something stopped being the case and nothing took its place. Returns 404 (and refunds the credit) if the key has no live fact. Costs 1 credit.

  • retrieve_memory

    Retrieve a stored memory by agent ID and key. Returns 404 (and refunds the credit) if the memory does not exist. Costs 1 credit.

  • retrieve_shared_memory

    Retrieve a value from a shared namespace by key. Costs 1 credit.

  • search_memories

    Case-insensitive text search across keys and values for a given agent. No embeddings or vector configuration required. Costs 1 credit.

  • store_assertion

    Record a fact that changes over time (a user's current plan, status, preference, or any value tied to an agent_id and key). To deliberately replace a specific earlier fact, pass its assertion_id in `supersedes`, which links the two so the history stays traceable. Writing WITHOUT `supersedes` to a key that already has a live value is allowed and creates a contested state that is surfaced on the next get_assertion — this is intended, not an error. Costs 1 credit.

  • store_memory

    Store a value under a key for a given AI agent. Writing to an existing key updates the value (no duplicates created). Costs 1 credit.

  • store_shared_memory

    Store a value in a shared namespace. Any agent with the namespace_key can write to it. Costs 1 credit.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Aug 12, 2026 (2 months ago)
Last release
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.seanmarkwei/agentram-mcp
Version
0.1.1
Auth
API key
Packages
npm agentram-mcp
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Agentram MCP running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Agentram MCP?

CallGet help
Cite this page

Agentram MCP. Agent Mart. https://agentmart.dev/connectors/seanmarkwei-agentram-mcp (last updated 2026-10-24)