conxt

Persistent AI memory layer for developers.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Get Context: Load relevant memories from your Conxt graph for the current task. Args: query: What you are working on or need context for user_id: Your Conxt user ID (optional — auto-resolved from API
  • Get Memories: List personal memories from your Conxt graph, with optional filters. Team memories are excluded — use get_team_memories for those. Args: user_id: Your Conxt user ID (optional — auto-reso
  • Search Decisions: Search your decisions and coding rules for a specific topic. Args: query: What decision or rule to search for user_id: Your Conxt user ID (optional — auto-resolved from API key)

What data it sees

Do you need an account

No: the server works without sign-in

Persistent AI memory layer for developers. Never re-explain your stack to AI tools again.

Conxt captures your decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf — and surfaces them automatically at the start of every new session.

8 MCP tools:

Setup: Generate an API key at conxt.dev/dashboard → Settings → API Keys. Takes 2 minutes.

Free tier: 200 memories. Pro: $9/mo. Team: $25/seat.

How to connect

How to connect conxt to Claude

The server address to paste into Claude settings:

https://conxt--pgavali0318.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect conxt to ChatGPT

The server address to paste into ChatGPT settings:

https://conxt--pgavali0318.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect conxt to Cursor

The server address to paste into Cursor settings:

https://conxt--pgavali0318.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (8)

Raw names from tools/list. Only developers need these.

get_context Load relevant memories from your Conxt graph for the current task. Args: query: What you are working on or need context for user_id: Your Conxt user ID (optional — auto-resolved from API key) limit: Max memories to return (default 15)
get_memories List personal memories from your Conxt graph, with optional filters. Team memories are excluded — use get_team_memories for those. Args: user_id: Your Conxt user ID (optional — auto-resolved from API key) memory_type: Filter by type — decision, preference, entity, open_question, coding_rule, tool_choice, workflow (optional) source: Filter by platform — claude, chatgpt, gemini, copilot, mcp (optional) date_from: Filter memories from this datetime — ISO format or natural e.g. "2026-05-24", "2026-05-24T15:40:00" (optional) date_to: Filter memories up to this datetime — ISO format (optional) limit: Max results (default 20)
search_decisions Search your decisions and coding rules for a specific topic. Args: query: What decision or rule to search for user_id: Your Conxt user ID (optional — auto-resolved from API key)
get_pinned Get your pinned memories — the most important permanent context. Args: user_id: Your Conxt user ID (optional — auto-resolved from API key)
add_memory Save a new personal memory to your Conxt graph. For team memories, use add_team_memory instead. Args: content: What to remember memory_type: decision, preference, entity, open_question, coding_rule, tool_choice, workflow user_id: Your Conxt user ID (optional — auto-resolved from API key)
list_my_teams List all teams you belong to, with their IDs. Call this first when the user wants to read or write team memories — you'll need the team_id from this list to pass to get_team_memories or add_team_memory. Args: user_id: Your Conxt user ID (optional — auto-resolved from API key)
get_team_memories Read memories belonging to a specific team workspace. Team memories are isolated from personal memories — only members of the team can read them. Call list_my_teams first if you don't know the team_id. Args: team_id: The team's UUID (get it from list_my_teams) memory_type: Filter by type — decision, preference, entity, open_question, coding_rule, tool_choice, workflow (optional) limit: Max results (default 20, max 50) user_id: Your Conxt user ID (optional — auto-resolved from API key)
add_team_memory Save a memory to a team workspace (visible to all team members). Use this when the user explicitly mentions a team or wants a decision shared with their team. For personal memories, use add_memory instead. Args: team_id: The team's UUID (get it from list_my_teams) content: What to remember memory_type: decision, preference, entity, open_question, coding_rule, tool_choice, workflow user_id: Your Conxt user ID (optional — auto-resolved from API key)