Trailweights MCP Server

by trailweights Your server? Claim it

not responding

Trailweights MCP is listed as active in the registry but did not answer our last check. It exposes 9 tools. Last commit 6 Sep 2026.

Verified ultralight gear evidence for agents: weights, specs, creator reviews, consensus. API key.

Uptime history 51 days of history · worst day 0%

51 days agonow

0.0%

Uptime 24h

0 of 91 checks

Tools

read from the server

613 ms

Response time

average over 24h

Stars

last commit 6 Sep 2026

What changed 8

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 12 August 2026. No other catalogue keeps this.

20 Sep 2 tool descriptions were rewritten compare_gear, get_product_specs

21 Aug a tool appeared report_outcome

21 Aug a tool changed version

12 Aug 2 tool descriptions were rewritten get_field_consensus, recommend_gear

12 Aug a tool changed the parameters it asks for get_field_consensus

12 Aug a tool changed version

Trailweights MCP does not always answer

Over the last week it answered 63.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add trailweights-mcp --transport http https://trailweights.com/api/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "trailweights-mcp": {
      "url": "https://trailweights.com/api/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.trailweights-mcp]
url = "https://trailweights.com/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "trailweights-mcp": {
      "url": "https://trailweights.com/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "trailweights-mcp": {
      "url": "https://trailweights.com/api/mcp"
    }
  }
}

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

compare

compare_gear

Side-by-side spec comparison for 2–6 products. Returns aligned rows of name, weight, price, category, buy URL and the full category spec sheet, each with a trust envelope (verified weight provenance, manufacturer-vs-field conflict flag, top citations). `comparable_fields` names the specs every compared product actually publishes, so an absent value is never read as a difference.

corpus

search_corpus

Semantic search over the TrailWeights knowledge corpus (transcripts, product descriptions, in-house pack templates, surveys, ultralight Bible). Returns the top matching chunks with source attribution. Supports hard predicates — filter by verified max weight (grams), max price (USD), minimum independent creator count (trust floor), and gear category — so hybrid semantic+spec queries resolve in one call.

field

get_field_consensus

Pre-computed field consensus for a product: what independent creators and the field say, scored on a deterministic 100-point rubric with a source-diversity gate. Returns the consensus label, score, evidence count, distinct authors, known conflicts, and a sample of the underlying evidence claims with source URLs. This is conflict-resolution an agent would otherwise have to reconstruct from raw reviews. Pass either the product UUID or the slug.

gear

get_gear_reviews

Fetch creator video reviews for a product. Returns up to 10 verified mentions with creator name, YouTube ID, timestamp, and quoted snippet.

lighter

find_lighter_alternative

Given a product, return up to 5 lighter alternatives in the same category, ordered by verified weight ascending. Each alternative carries a trust envelope (verified weight provenance, conflict flag, top citations).

pack

get_pack_template

Return one of the 21 in-house TrailWeights pack templates by ID or slug, including the full item list and total weight.

product

get_product_specs

Canonical product spec sheet — name, brand, category, verified weight, MSRP, image, and a cottage-first affiliate buy URL. Returns the full category spec vocabulary in `specs` (floor area and peak height for a shelter, R-value and thickness for a pad, fill power and temperature rating for a quilt), each row carrying a human label, a formatted display value, and — where the value came through the verified extraction lane — the maker's page URL and the verbatim sentence it was read from. Also includes a trust envelope: verified weight with provenance (measured vs manufacturer claim), confidence, last-verified date, a manufacturer-vs-field weight conflict flag, and top creator citations with source URLs. Pass either the product UUID or the slug.

recommend

recommend_gear

Deterministic, fast (<500ms) structured gear lookup from a freeform query (e.g. 'best quilt for a PCT thru hike'). Runs the TrailWeights deterministic query planner — rule-based category/intent detection, brand-alias expansion, and compiled weight/price/category constraints; no server-side LLM is invoked. Returns the top catalog products ranked by the compiled plan (verified weight, relevance, price) with verified weights (provenance and conflict flags), trust envelopes with field-consensus signal, citations, and cottage-first buy URLs, plus the applied filters. The calling agent supplies the reasoning; this tool supplies verified data. Optional weight cap (oz) and category filter.

report

report_outcome

Optionally report whether a prior TrailWeights MCP result was used, cited, or helpful. The request_id must come from that result and the reporting caller must match the original caller. This writes telemetry only; it never changes catalog or account data.

Endpoints

URL	Transport	State	Latency	Checked
https://trailweights.com/api/mcp	streamable-http	answering	613 ms	12 min ago

Alternatives to Trailweights MCP

same job, measured the same way

Agent Evidence API

by thx93

MCP-native web evidence and claim verification: cited, source-grounded evidence for AI agents.

2 tools answering

Elite Reasoning MCP

by snehgabani

Evidence-gated verification, selection, and measurement MCP for coding agents.

43 installs/wk local only

Verirun

by baopeak

Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.

199 installs/wk local only

Evr

by brienbounded

Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.

114 installs/wk local only

Layrcake

by layrcake

Unified GTM API for AI agents: find, enrich, verify, intent, sending, campaigns, replies. One key.

answering

AccordTrace

by kosta1985

Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.

9 tools answering

California Bitcoin

by californiabitcoin

Bitcoin research for AI agents: free answers, specialist Q&A, verification, evidence, timelines.

12 tools answering

MCP x402 - Evidence-Backed Web Verification

by diogoup26

Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.

3 tools answering

Trailweights MCP — questions

Answers built from our own checks of this server.

What can Trailweights MCP do?

It exposes 9 tools, read directly from the server on our last check. Among them: compare_gear, find_lighter_alternative, get_field_consensus, get_gear_reviews, get_pack_template, get_product_specs and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Trailweights MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 613 ms. The bar chart above shows every period we have measured.

The registry lists Trailweights MCP as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Trailweights MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Trailweights MCP need an API key?

No. Trailweights MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.

Is Trailweights MCP open source?

Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.