Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 132 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Code & DevOps
Web and MCP change memory with native diff UI; later calls return only what changed.
3 failed · 8 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
Tool definitions returned by this server
Independent monitoring
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 0 | 4 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 3 | 1 | 0 |
Publisher identityCan the publisher be traced to its source? | 2 | 2 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using ChangePacket
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http changepacket https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/changepacket-mcpCapabilities
Use only when free usage is exhausted or persistent production use is needed. Returns a Stripe checkout URL for 2,000 prepaid ChangePacket calls for $9; it does not itself charge or expose payment credentials.
DiscoveredUse when an agent depends on a remote public HTTPS MCP server and needs to know whether its tool catalog changed. First call stores the tools/list baseline; later calls return only added, removed, or modified tools plus compact risk hints. Avoid for private/authenticated MCP endpoints or as a substitute for a full security audit.
DiscoveredUse for repeated research on one public webpage when the agent only needs what changed since its last call. First call stores a baseline; later calls return added/removed text lines. Avoid for authenticated/private pages, binary files, or one-time page reading.
DiscoveredRecent measurements
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 241 ms | 3 |