MCP Boundary
Blocks MCP tool calls with reasons the agent can act on
Hype can't move this line. Only verifiable outcomes do.
No money. No seat. It doesn't move the price. It goes on your record — and in 28 days reality settles it.
by reality anchor — the price money can't pump
AI. Launched 6d ago on PeerPush, where it placed #475. Today, it's live, but nothing on the site has changed since we started watching. It's anchored at 1,055 pts.
It placed #475 on PeerPush with 12 votes.
A launch's opening price comes from where it placed on its own board, normalised across all 12 platforms we watch. That's deliberate: #1 on a small board beats #40 on a huge one. It's how a launch nobody saw can still be worth more than one everybody did.
No matter how much money goes in. There is no pump here — you can't make yourself right by buying more. The line only moves on things that actually happened: an award, revenue that grew, a new platform, code that shipped — or silence.
Quiet for 3 days — no penalty yet. Bleeding begins on day 7.
We fetch this site every day and hash what's on it. A founder can post “still working on it” — but if they actually shipped, the page changes. That's the only claim we price: evidence, not announcements. The real question isn't “will this be huge?” — it's “will they still be moving in four weeks?”
The story so farEVERY MOVE, AND WHY▾
1 quiet day in between are left out — nothing happened on them. Repriced every day, no cliffs. A launch that goes quiet bleeds a little at a time, so there's never a drop you could have run from the night before.
Momentum on its boardDOESN'T MOVE THE PRICE▾
Daily tracking just started for this launch — the first point is on the board. A second reading lands with tomorrow's run, and the curve builds from there.
How the launch is moving on its own board, day by day. This is the crowd's attention — it does not move the reality price. Only verifiable outcomes do.
A flat line is normal: votes stop within a day or two of launch, on every board. What's unusual — and what actually counts — is a launch that keeps pulling votes long after its day is over.
About
MCP Boundary is a local checkpoint between your AI agent - for example Claude Desktop - and the MCP tools it uses. You write the rules; Boundary checks each routed call against them before it runs. Nothing here is automatic - it does what your policy says. The point is not just to say no. When Boundary blocks a call, it sends back a short, machine-readable reason the agent can use, so the agent can adjust the request instead of failing or retrying blindly. Two things make that useful. State-aware writes. One rule you can set is to tie a write to the data the agent read first. Then, if that data changed in the meantime, Boundary stops the write and tells the agent to read again before acting. A valid call is not always a safe outcome. Clear feedback, and human approval when it matters. A block is not a dead end. The reason can be specific - for example, which email recipients were rejected, so the agent can retry without them. And for a call that needs a person's OK, nothing runs: the agent gets a clear "waiting for approval" answer and pauses, while a human approves or rejects the exact action in the local dashboard. Only an approved follow-up call goes through. Your rules can reach into the details of a call, not just its name: which recipients are allowed, which values are permitted, how much data can come back, how often a call may repeat. Every checked call - the decision, the reason, the result - lands in a local activity view, so you can see what the agent tried and why it was allowed or blocked. It all runs on your machine. The agent sees the tools, never the passwords or tokens behind them, and nothing is sent back to us. About prompt injection: Boundary does not try to detect a jailbreak or a poisoned instruction. It works one layer lower. Even if the model is tricked, routed calls can still only do what your policy allows - so a risky send, write, or delete that your policy blocks stays blocked, or waits for a human, no matter why the agent asked. Honest scope: Boundary only checks calls that actually run through it. It does not vouch for what an MCP server does inside, and it is a local tool for developers and operators — not a hosted security gateway or a data-loss filter.
Where it launched1 PLATFORM▾
| Platform | Votes | Counts toward price | Link |
|---|---|---|---|
| PeerPush | 12 | sets the price | ↗ |
The board it did beston sets the price. Every other board only adds to it if the launch also landed in that board's top 25% — because just showing up somewhere isn't an achievement. Listing on twelve directories is free; placing well on them isn't.