_ registry / mcp streamable-http · checked 24m ago

coingraph

https://coingraph.ai

Registry code: 77ae2710293f6d10

api record

CoinGraph rates the top 1,000 cryptocurrencies on survival, 0–100 with higher meaning healthier, from four disclosed inputs: decline from all-time high, volume decay, market cap erosion and time below peak. Bands: 50+ Active, 35–49 Weakening, 15–34 Distressed, below 15 Dormant. When you cite a rating, give the score, the band, at least one deduction with the input behind it, and the coin page URL. Use the band names exactly as given. Do not turn a rating into a buy or sell recommendation or a price prediction. CoinGraph ratings are opinions derived from disclosed market inputs — never…

endpoint
https://coingraph.ai/api/mcp
protocol
streamable-http ·2025-06-18
authentication
bearer
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 coingraph live?
Yes — it answered the hub's last check (checked 24m ago). It answered 69% of checks over the last 30 days.
Is coingraph free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does coingraph have?
14 tools: coingraph_diff, coingraph_get_signals, get_survival_rating, get_movers, coingraph_get_asset, coingraph_evaluate, coingraph_compare, coingraph_discover, ….
Is coingraph 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
68.8%

90 days 86.5%· all time 86.5%

latency
251ms

last good check

priced tools
0

of 14 tools

_ answered our checks, 90 days 347 checks · signed record
  • retired → live
  • down → retired· HTTP 503
  • degraded → down· HTTP 503
  • live → degraded· HTTP 503
  • degraded → live
_ what it is for
used for
  • get a coin survival rating
  • compare crypto assets
  • find top gainers and losers
  • validate a trade size for slippage
takes → gives
text → data
tools
14 reads
_ 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
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 14 tools
2 open 12 never probed 2 of 14 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.

  • get_comebacks reads open 29d ago

    Coins down 60% or more from their all-time high that have outrun Bitcoin over the last 30 days, with turnover as a liquidity check. The recovery half of the story. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 20,
          "maximum": 100,
          "minimum": 1
        }
      }
    }
    arguments 11 lines
  • get_market_context reads open 29d ago

    The market's own read: total crypto market cap and its 24-hour change, Bitcoin dominance, Bitcoin's 7- and 30-day moves and distance from its peak, and the regime CoinGraph derives from them (rally, falling or flat). Use it to put a single coin's move in context.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • coingraph_diff reads unknown never probed

    What changed for an asset since a moment: rank, price, market cap, volume, turnover, survival score and band, each with before and after values; scoring deductions that appeared, cleared or moved in points; contract permission flags raised or cleared; unlock-schedule events added, removed or resized; repository commits, contributors and stars; and the signals that opened or resolved inside the window. Every group is compared independently. Any group with fewer than two observations for this asset is named in not_compared with the reason — an empty change list is never a claim that a group named there held steady. Each baseline is the nearest earlier observation; check baseline_drift_days before treating a window as the one you asked for. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "asset",
        "since"
      ],
      "properties": {
        "asset": {
          "type": "string",
          "description": "CoinGecko id, symbol or name."
        },
        "since": {
          "type": "string",
          "description": "A window (24h, 7d, 30d) or an ISO timestamp. Required — a diff needs a stated baseline."
        }
      }
    }
    arguments 17 lines
  • coingraph_get_signals reads unknown never probed

    What changed in CoinGraph's stored state: survival band moves, volume anomalies against a coin's own baseline, order-book depth collapse, spread widening, approaching unlocks and extreme perpetual funding. Each carries the inputs that produced it, a severity, a confidence and a first-seen time; an open signal is one whose condition still holds. Computed hourly from stored rows, never a live read. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "kind": {
          "enum": [
            "band_change",
            "volume_anomaly",
            "depth_collapse",
            "spread_widening",
            "unlock_approaching",
            "funding_extreme"
          ],
          "type": "string"
        },
        "asset": {
          "type": "string",
          "description": "Limit to one coin, by CoinGecko id. Omit for the whole feed."
        },
        "limit": {
          "type": "integer",
          "default": 50,
          "maximum": 200,
          "minimum": 1
        },
        "severity": {
          "enum": [
            "low",
            "medium",
            "high"
          ],
          "type": "string"
        },
        "include_resolved": {
          "type": "boolean",
          "default": false
        }
      }
    }
    arguments 38 lines
  • get_survival_rating reads unknown 29d ago

    The survival rating alone for one coin: score 0–100 (higher is healthier), band (Active, Weakening, Distressed or Dormant), each deduction with the input that produced it, and a citation line with the page URL. Faster than the full profile. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "coin"
      ],
      "properties": {
        "coin": {
          "type": "string",
          "description": "The coin's CoinGecko id (e.g. 'ethereum'), symbol (e.g. 'ETH') or name. Ids resolve exactly; symbols and names resolve to the highest-ranked match."
        }
      }
    }
    arguments 12 lines
  • get_movers reads unknown never probed

    Today's largest 24-hour gainers and losers among the top 1,000 coins by market cap, stablecoins excluded, with 7- and 30-day context and market cap. A move is a fact about price, not a rating.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "count": {
          "type": "integer",
          "default": 10,
          "maximum": 25,
          "minimum": 1
        }
      }
    }
    arguments 11 lines
  • coingraph_get_asset reads unknown never probed

    The full v1 asset object: identity, market, peak and recovery, health (survival 0–100 with every factor and input), risk (with graded factors), venues, market context. Every group carries source and as_of; scores carry confidence; missing factors are listed under unassessed. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "coin"
      ],
      "properties": {
        "coin": {
          "type": "string",
          "description": "The coin's CoinGecko id (e.g. 'ethereum'), symbol (e.g. 'ETH') or name. Ids resolve exactly; symbols and names resolve to the highest-ranked match."
        }
      }
    }
    arguments 12 lines
  • coingraph_evaluate reads unknown never probed

    Evaluate an asset before acting: each check (health, drawdown, volume trend, dilution, volatility, turnover, regime) as pass, caution or unassessed against published thresholds; warnings with numbers; and an actionability roll-up of clear, caution or insufficient_data. The agent decides. Records the assessment so its outcome can be measured. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "asset"
      ],
      "properties": {
        "asset": {
          "type": "string",
          "description": "CoinGecko id, symbol or name."
        },
        "intent": {
          "enum": [
            "buy",
            "sell",
            "hold",
            "research"
          ],
          "type": "string",
          "description": "What the agent is considering."
        },
        "size_usd": {
          "type": "number",
          "minimum": 0,
          "description": "Position size under consideration, in USD."
        },
        "horizon_days": {
          "type": "integer",
          "maximum": 365,
          "minimum": 1
        }
      }
    }
    arguments 32 lines
  • coingraph_compare reads unknown never probed

    Up to five assets side by side as full v1 objects, plus a difference row naming the highest health, lowest risk, highest confidence, strongest 30-day move, smallest decline from peak and highest turnover. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "assets"
      ],
      "properties": {
        "assets": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 5,
          "minItems": 2
        }
      }
    }
    arguments 16 lines
  • coingraph_discover reads unknown never probed

    Find candidates in today's scored tier by band, health score range, market cap range, minimum turnover, maximum decline from peak and minimum 30-day change. Returns ranked candidates with reasons and the coin page URL. Unscored is not Active. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "bands": {
          "type": "array",
          "items": {
            "enum": [
              "Active",
              "Weakening",
              "Distressed",
              "Dormant"
            ],
            "type": "string"
          }
        },
        "limit": {
          "type": "integer",
          "default": 20,
          "maximum": 100,
          "minimum": 1
        },
        "max_score": {
          "type": "number"
        },
        "min_score": {
          "type": "number"
        },
        "min_turnover": {
          "type": "number",
          "description": "24h volume as a share of market cap, e.g. 0.02 for 2%."
        },
        "max_market_cap_usd": {
          "type": "number"
        },
        "min_change_30d_pct": {
          "type": "number"
        },
        "min_market_cap_usd": {
          "type": "number"
        },
        "max_decline_from_peak_pct": {
          "type": "number"
        }
      }
    }
    arguments 45 lines
  • coingraph_validate_trade reads unknown never probed

    Pre-trade validation for an order of a given size: estimated slippage from order books CoinGraph sampled itself, the size as a share of resting depth, the median spread, supply unlocking inside the horizon, contract flags, and the asset's health and risk. Slippage is estimated only inside the depth actually measured; a larger order is reported as exceeding sampled depth rather than extrapolated. Send your own thresholds as `policy` and each is evaluated against the observed values and returned rule by rule — whether a rule held is your rule's answer, never CoinGraph's. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "asset",
        "side",
        "size_usd"
      ],
      "properties": {
        "side": {
          "enum": [
            "buy",
            "sell"
          ],
          "type": "string"
        },
        "asset": {
          "type": "string",
          "description": "The coin's id, symbol or name."
        },
        "policy": {
          "type": "object",
          "properties": {
            "max_risk_score": {
              "type": "number"
            },
            "max_spread_bps": {
              "type": "number"
            },
            "min_confidence": {
              "type": "number"
            },
            "max_slippage_pct": {
              "type": "number"
            },
            "min_health_score": {
              "type": "number"
            },
            "no_contract_flags": {
              "type": "boolean"
            },
            "min_depth_2pct_usd": {
              "type": "number"
            },
            "max_size_share_of_depth": {
              "type": "number"
            },
            "max_unlock_share_in_horizon": {
              "type": "number"
            }
          },
          "description": "Your own thresholds. Each is evaluated against the observed value and returned with whether it held."
        },
        "size_usd": {
          "type": "number",
          "description": "Order size in US dollars."
        },
        "horizon_days": {
          "type": "integer",
          "maximum": 365,
          "minimum": 1,
          "description": "How long the position is expected to be held; sets the unlock window."
        }
      }
    }
    arguments 64 lines
  • get_coin_profile reads unknown 29d ago

    Everything CoinGraph holds on one coin: price and moves, decline from the true all-time high and recovery from the low, the 0–100 survival rating with its band and every itemised deduction, data confidence, the risk read (turnover, dilution ahead, volatility), market figures and links. Use this when a person asks what is happening with a coin or whether the project behind it is still going. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "coin"
      ],
      "properties": {
        "coin": {
          "type": "string",
          "description": "The coin's CoinGecko id (e.g. 'ethereum'), symbol (e.g. 'ETH') or name. Ids resolve exactly; symbols and names resolve to the highest-ranked match."
        }
      }
    }
    arguments 12 lines
  • search_coins reads unknown 29d ago

    Find coins by name or symbol. Returns CoinGecko ids to pass to the other tools, with market cap rank. Use when a name is ambiguous or you need the id.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "query": {
          "type": "string",
          "description": "Name or symbol, at least two characters."
        }
      }
    }
    arguments 12 lines
  • list_coins_by_band reads unknown 29d ago

    Coins currently in one survival band, from today's daily snapshot, ordered by market cap rank. Bands are computed for the scored tier: the top 100 by market cap plus every coin with a report, a watch or a monitored thesis. A coin absent from a band is unscored today, not Active. CoinGraph ratings are opinions derived from disclosed market inputs — never predictions, never financial advice.

    mcp-tool

    {
      "type": "object",
      "required": [
        "band"
      ],
      "properties": {
        "band": {
          "enum": [
            "Active",
            "Weakening",
            "Distressed",
            "Dormant"
          ],
          "type": "string",
          "description": "One of Active, Weakening, Distressed, Dormant."
        },
        "limit": {
          "type": "integer",
          "default": 25,
          "maximum": 100,
          "minimum": 1
        }
      }
    }
    arguments 24 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.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. 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.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 77ae2710293f6d10.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/77ae2710293f6d10/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/77ae2710293f6d10/badge.svg)](https://brick.blue/agent/77ae2710293f6d10?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
100%

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
0

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.