Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

Agentage Memory MCP Server for Claude

Remote Agentage Memory MCP server giving Claude one shared, portable memory across every AI you use - search, read, write, edit, list, and delete plain Markdown notes you own, over Streamable HTTP with OAuth 2.1.

by agentage·added 2026-06-18·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • The memory__write, memory__edit, and memory__delete tools create, modify, and remove your stored notes; review actions before granting broad access.

Privacy notes

  • Notes you read or write are stored server-side in your Agentage Memory and mirrored locally as Markdown you can export anytime; note contents pass through model context.

Prerequisites

  • agentage account (sign in at memory.agentage.io)
  • OAuth 2.1 authentication (PKCE + Dynamic Client Registration, handled in the connect flow)
  • Network access to memory.agentage.io (HTTPS required)
  • Claude Desktop 0.7.0+ or Claude Code with MCP (HTTP transport) support

Schema details

Install type
cli
Troubleshooting
No
Collection metadata
Estimated setup
1 minute
Difficulty
beginner
Tool listing metadata
Full copyable content
{
  "agentage-memory": {
    "url": "https://memory.agentage.io/mcp",
    "transport": "http"
  }
}

About this resource

Content

Connect Claude to Agentage Memory, the shared memory layer for every AI. One Markdown memory that Claude, Cursor, and ChatGPT can all read and write through MCP, mirrored locally as plain .md files you own and can export anytime. The remote server speaks Streamable HTTP with OAuth 2.1, PKCE, and Dynamic Client Registration, so connecting is a one-time browser sign-in.

Features

  • One shared memory across Claude, Cursor, ChatGPT, and any MCP client
  • Plain-Markdown notes you own, mirrored locally and exportable anytime
  • Full-text search across your memory (memory__search)
  • Read, write, edit, list, and delete notes (memory__read / write / edit / list / delete)
  • Remote hosted server - no local install or runtime to maintain
  • OAuth 2.1 + PKCE + Dynamic Client Registration for secure, per-client access

Use Cases

  • Carry context, decisions, and preferences between different AI tools
  • Build a durable personal or team knowledge base your AIs read and update
  • Search past notes before starting new work
  • Keep an owned, exportable Markdown record instead of vendor-locked memory

Installation

Claude Code

  1. Run: claude mcp add --transport http agentage-memory https://memory.agentage.io/mcp
  2. Verify installation: claude mcp list
  3. Authenticate with your agentage account (OAuth flow opens in browser)

Claude Desktop

  1. Open your Claude Desktop configuration file
  2. Add the Agentage Memory server configuration (HTTP transport, URL https://memory.agentage.io/mcp)
  3. Restart Claude Desktop
  4. Authenticate with your agentage account (OAuth flow)

Configuration

{
  "agentage-memory": {
    "url": "https://memory.agentage.io/mcp",
    "transport": "http"
  }
}

Security

  • OAuth 2.1 + PKCE required for access; unauthenticated requests return 401
  • Protected Resource Metadata (PRM) is served for discovery
  • Dynamic Client Registration issues per-client credentials
  • Tokens are bearer credentials - store securely, never commit to a repo
#memory#knowledge#markdown#oauth#agentage

Source citations

Add this badge to your README

Show that Agentage Memory MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/agentage-memory-mcp-server.svg)](https://heyclau.de/entry/mcp/agentage-memory-mcp-server)

How it compares

Agentage Memory MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldAgentage Memory MCP Server for Claude

Remote Agentage Memory MCP server giving Claude one shared, portable memory across every AI you use - search, read, write, edit, list, and delete plain Markdown notes you own, over Streamable HTTP with OAuth 2.1.

Open dossier 		Basic Memory MCP Server

Local-first Basic Memory MCP server for giving Claude a persistent Markdown knowledge base with note editing, semantic search, recent activity, knowledge graph context, projects, schema tools, and optional cloud sync.

Open dossier 		AutoRFP.ai MCP Server for Claude

Official AutoRFP.ai remote MCP server for read-only access to RFP projects, requirements, approved content library search, and organisation tags from Claude and other MCP clients via OAuth.

Open dossier 		Auxen MCP Server for Claude

Official Auxen.ai remote MCP server for listing GPU models and instances, checking account balance, and provisioning or destroying inference instances from Claude via OAuth 2.1 or API keys.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categorymcpmcpmcpmcp
Sourcesource-backedsource-backedsource-backedsource-backed
AuthoragentageBasic MachinesAutoRFP.aiAuxen AI
Added2026-06-182026-06-062026-06-142026-06-14
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓The memory__write, memory__edit, and memory__delete tools create, modify, and remove your stored notes; review actions before granting broad access.✓Basic Memory MCP can create, edit, move, and delete notes in the configured project. The server exposes content, search, knowledge graph, project, schema, cloud, and release-note tools. Edit and delete tools should be reviewed carefully because the model can change the human-readable Markdown source of truth. Imports can ingest Claude, ChatGPT, or memory JSON exports and may bring old sensitive conversations into the knowledge base. Auto-update behavior can update uv tool and Homebrew installs, while uvx runs use the ephemeral runtime managed by uv. The optional cloud service changes the trust boundary by syncing notes through hosted storage and account authentication.✓The connection is read-only; it cannot create, edit, or delete AutoRFP.ai records. Each user inherits their own AutoRFP.ai permissions, so MCP results reflect that user's normal app access. OAuth tokens grant persistent read access until revoked in AutoRFP.ai or the MCP client. Do not share OAuth-approved connector sessions across users or paste access tokens into public issues.✓provision_model creates billable GPU instances; confirm model, region, and cost before approving tool calls. destroy_instance permanently removes running instances and cannot be undone through MCP. API keys prefixed auxen_live_* operate on production resources; use auxen_test_* keys in development. OAuth tokens grant persistent account access until revoked in Auxen or the MCP client.
Privacy notes✓Notes you read or write are stored server-side in your Agentage Memory and mirrored locally as Markdown you can export anytime; note contents pass through model context.✓Local notes, frontmatter, wikilinks, observations, relations, embeddings, logs, and project metadata can contain personal data, credentials, customer details, unreleased plans, or private research. Cloud routing and hosted team workspaces may sync Markdown, metadata, snapshots, and backups outside the local machine. The README says telemetry records non-content usage events and does not collect file contents, note titles, knowledge base data, PII, IP addresses, or per-tool tracking. Logs are written to Basic Memory's local log file by default for MCP usage; review log level and retention before using sensitive prompts or notes. Keep API keys, cloud credentials, imported chat archives, and private project paths out of prompts, screenshots, issues, and committed files.✓MCP tool results can expose RFP project names, requirement text, approved answer content, and organisation tag vocabulary. Search queries sent to the content library are processed by AutoRFP.ai under its own data-handling terms. Public support notes should describe connector scope, not full requirement or library excerpts.✓MCP tool results can expose account balance, instance IDs, model names, and deployment metadata. Provisioning requests are processed by Auxen.ai under its own data-handling and billing terms. Do not paste live API keys or OAuth tokens into public issues or shared chat logs.
Prerequisites
  • agentage account (sign in at memory.agentage.io)
  • OAuth 2.1 authentication (PKCE + Dynamic Client Registration, handled in the connect flow)
  • Network access to memory.agentage.io (HTTPS required)
  • Claude Desktop 0.7.0+ or Claude Code with MCP (HTTP transport) support
  • Python 3.12 or newer available through uv for the local MCP server.
  • A selected Basic Memory project directory for Markdown notes and generated metadata.
  • Backups or version control for important notes before enabling model-assisted writes.
  • Team agreement on whether notes stay local, sync through the optional cloud service, or route per project.
  • AutoRFP.ai account with access to the projects and content library you want to query.
  • Claude Pro, Team, or Enterprise plan with Connectors support, or another MCP client with custom remote connectors.
  • Claude organisation admin for the one-time org connector setup in Claude Team/Enterprise environments.
  • Knowledge of your AutoRFP.ai data residency region (APAC, EU, or US) to select the correct MCP endpoint.
  • Auxen.ai account with billing enabled for production instance provisioning.
  • Claude Pro, Team, or Enterprise with Connectors support, or another MCP client with remote HTTP connectors.
  • OAuth 2.1 + PKCE flow support in your MCP client, or an Auxen API key prefixed with auxen_live_ or auxen_test_.
  • Understanding that provision_model and destroy_instance are destructive and may incur GPU charges.
Install
claude mcp add --transport http agentage-memory https://memory.agentage.io/mcp && claude mcp list
claude mcp add basic-memory -- uvx basic-memory mcp
claude mcp add --transport http autorfp https://api.autorfp.ai/mcp
claude mcp add --transport http auxen https://api.auxen.ai/mcp
Config
{
  "mcpServers": {
    "agentage-memory": {
      "url": "https://memory.agentage.io/mcp",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "basic-memory": {
      "command": "uvx",
      "args": ["basic-memory", "mcp"]
    }
  }
}
{
  "mcpServers": {
    "autorfp": {
      "url": "https://api.us.autorfp.ai/mcp",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "auxen": {
      "url": "https://api.auxen.ai/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer auxen_live_YOUR_KEY"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.