MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

ClearMarket

Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance.

Checks passed
13 / 22

2 failed · 7 not measured

Median response
73 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
6

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 96 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name clearmarket.

  • Pass
    Lists tools

    tools/list returned 6 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 73 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 94 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    8 of 16 parameters have a description (50%). The bar is 80%.

  • Fail
    Safety hints

    6 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-06-09T15:37:45.948598Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using ClearMarket

Connect to this server

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 clearmarket https://api.clearmarket.fyi/mcp

Capabilities

Tools 6

get_event

Fetch the full ClearMarket record for one event by slug: the canonical question, every market in this event's single-venue bundle, each market's current price + Resolution Clarity Grade (A/B/C) + resolution-source provenance, the canonical question_id where the question is linked across venues/events (null otherwise; also_on lists the same question priced on the other venue, when it trades there), and the upcoming catalyst dates that move it before it resolves. In the default detail="full", each market in the bundle is FULLY detailed (grade, rcg.caps, provenance, direction, settlement_style, also_on) — you do not need a separate get_market call for markets already in this event. Note: a shared question_id means same topic across venues; in rare cases it links structurally-different contracts (e.g. a "hike" vs a "cut-count" market), so verify the contract shape before treating two as an arbitrage pair. Use when you need the authoritative, graded view of a SPECIFIC event — including its cross-venue twins via also_on — before reasoning about or acting on a prediction market. If you only have a topic (not a slug), call list_events first. Set detail="concise" for a quick grade/price/source check (each market trimmed to the essentials — much smaller for events with many markets); use the default detail="full" when you need every market's rules, contract shape, and complete provenance.

Discovered
get_market

Fetch one market and judge whether its price can be trusted. Accepts whatever id you have: a ClearMarket id (CM-MKT-…), a venue-native market id or Kalshi ticker, or a market URL (best-effort — Kalshi tickers / a native id in the path resolve; for Polymarket pass the conditionId, not the slug URL). Returns: raw question, current price / implied probability, the Resolution Clarity Grade with rcg.score (0-100) and rcg.caps (a cap such as "uncommitted_placeholder" hard-limits the grade — that is why a single-source market can still be C), full resolution provenance (arbitration_model = who resolves it, named source, source_type, and a graded source_status on EVERY market: named / no-committed-source / none / unknown), the contract shape (direction, settlement_style, threshold), the canonical question_id where linked, and also_on (the same question priced on other venues). The returned market_id is ALWAYS the canonical ClearMarket id (CM-MKT-…) — store and reuse THAT, not the venue id. Use before trusting or acting on a price.

Discovered
get_signal

Fetch one full CM Signal wire by slug: headline, the 3-5 structured bullets, atomic claims with per-field provenance tiers, the target + linked events, primary and related markets with prices, and sources. Use when you have a wire slug (from list_signals) and need the complete bulletin with its proof chain.

Discovered
list_events

Browse or search ClearMarket prediction-market events. Filter by category, platform, Resolution Clarity Grade, or free-text `q`. `q` is token-AND across question + tags, so SHORT KEYWORD queries match best ("microstrategy bitcoin", "fed rate") — natural-language phrases often return nothing. Returns compact graded summaries: slug, question, venues_covered, primary grade, rcg_score (0-100, for ranking clarity), last_price, and status (open / resolved). Start here when you have a topic but not a slug; then call get_event for the full graded record. Categories: economics, financials, crypto, companies, technology, politics, geopolitics, health, climate.

Discovered
list_signals

Browse the CM Signal daily wire — short, structured prediction-market bulletins (the price is the lede, news is context). Filter by event_id (every wire touching a specific event), category, venue, or detection type (news_cycle, cross_venue_divergence, benchmark_drift, volume_spike). Returns compact records, newest first; call get_signal for the full bulletin. Use to find ClearMarket's editorial read on what is moving.

Discovered
list_upcoming_catalysts

List scheduled catalysts (CPI, jobs, FOMC, GDP, large-cap earnings) in the next N days that move prediction-market prices BEFORE those markets resolve — a cross-event view across the whole calendar. Each entry is provenanced to its authoritative source (BLS, Fed, etc.). Use to find what scheduled events will reprice the prediction-market universe soon.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected96 ms6
Connected49 ms6