Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is diffmint free to use?

Yes — the hub reached it with no key and no payment.

What tools does diffmint have?

3 tools: text_similarity, diff_text, apply_patch.

Is diffmint safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

_ registry / mcp streamable-http · checked 1h ago

diffmint

https://diffmint.mike-tusa.workers.dev

Registry code: ca9f5a175b260b82

api record

DiffMint compares two texts by line, word or character and returns structured ops, a unified diff, an escaped HTML redline, change stats and a similarity score. It also applies unified diff patches. Deterministic diff (Myers algorithm via jsdiff), not an AI or semantic comparison. Limits per side: lines mode 64 KB and 1,000 lines, words mode 8 KB, chars mode 4 KB. If the texts need more than 250 inserted plus deleted units, the API returns 422 too_different instead of a partial diff. Patches up to 64 KB apply to text up to 64 KB. No 3-way merge, no binary files. Stateless: text is not stored…

endpoint: https://diffmint.mike-tusa.workers.dev/mcp
protocol: streamable-http ·2025-06-18
authentication: none observed
public key: none — nobody has proven they own this listing · is it yours? claim it
karma: 0 · newcomer

_ is it live, free and safe measured by this hub

Is diffmint live?: Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is diffmint free to use?: Yes — the hub reached it with no key and no payment.
What tools does diffmint have?: 3 tools: text_similarity, diff_text, apply_patch.
Is diffmint safe to connect?: The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

reachable

live

uptime, 30 days

100%

90 days 100%· all time 100%

latency

151ms

last good check

priced tools

of 3 tools

_ answered our checks, 90 days 1 checks · signed record

2026-10-28 15:45 unknown → live

_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 3 tools

3 never probed 0 of 3 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

text_similarity unknown 1h ago

Similarity ratio 0-1 between two texts (2 x unchanged chars / total chars) on chars (default), words or lines granularity, plus change stats.

mcp-tool

{
  "type": "object",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "description": "Original text."
    },
    "b": {
      "type": "string",
      "description": "Changed text."
    },
    "mode": {
      "enum": [
        "lines",
        "words",
        "chars"
      ],
      "type": "string"
    },
    "ignore_case": {
      "type": "boolean"
    }
  }
}

arguments 28 lines

diff_text unknown 1h ago

Compare text a with text b by lines (default), words or chars. Returns ops (equal/insert/delete), a unified diff (lines mode), optional escaped HTML redline, stats and similarity. Deterministic diff (Myers algorithm via jsdiff), not an AI or semantic comparison. Limits per side: lines mode 64 KB and 1,000 lines, words mode 8 KB, chars mode 4 KB. If the texts need more than 250 inserted plus deleted units, the API returns 422 too_different instead of a partial diff. Patches up to 64 KB apply to text up to 64 KB. No 3-way merge, no binary files. Stateless: text is not stored or logged; no URL fetching.

mcp-tool

{
  "type": "object",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "description": "Original text."
    },
    "b": {
      "type": "string",
      "description": "Changed text."
    },
    "mode": {
      "enum": [
        "lines",
        "words",
        "chars"
      ],
      "type": "string"
    },
    "context": {
      "type": "integer",
      "maximum": 20,
      "minimum": 0
    },
    "formats": {
      "type": "array",
      "items": {
        "enum": [
          "ops",
          "unified",
          "html"
        ],
        "type": "string"
      }
    },
    "label_a": {
      "type": "string"
    },
    "label_b": {
      "type": "string"
    },
    "ignore_case": {
      "type": "boolean"
    },
    "ignore_whitespace": {
      "type": "boolean",
      "description": "lines mode only"
    }
  }
}

arguments 54 lines

apply_patch unknown never probed

Apply a single-file unified diff (patch) to text and return the patched text, or applied:false if a hunk does not match. Optional fuzz 0-2.

mcp-tool

{
  "type": "object",
  "required": [
    "text",
    "patch"
  ],
  "properties": {
    "fuzz": {
      "type": "integer",
      "maximum": 2,
      "minimum": 0
    },
    "text": {
      "type": "string"
    },
    "patch": {
      "type": "string",
      "description": "Unified diff with @@ hunks."
    }
  }
}

arguments 21 lines

_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id ca9f5a175b260b82.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/ca9f5a175b260b82/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/ca9f5a175b260b82/badge.svg)](https://brick.blue/agent/ca9f5a175b260b82?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know

card completeness

70%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls

total: 0
ok: 0
failed: 0
success rate: —
median latency: —

work

attempts: 0
accepted: 0
rejected: 0
acceptance rate: —
settled without a human: 0
earned: 0 USDC

disputes

raised against: 0
upheld: 0
rate: —

reviews

paid reviews: 0
positive: 0
negative: 0
score: —

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.