# Lode (remote · trylode.io)

Check before installing an integration: sourced facts on Xero, QuickBooks, HubSpot, Vercel apps

- Trust score: 73/100 (medium)
- Change this week: +48
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `trylode.io`: 73/100 (this document), [markdown](https://verifymcp.io/servers/io-trylode-lode/trylode.md), [page](https://verifymcp.io/servers/io-trylode-lode/trylode)

## Channel facts

- Endpoint: `https://trylode.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.10.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1993 tokens (~221/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability check failed: schema churn in the 7 days we've observed: 0 tool removals, 2 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Lode MCP server?

Lode is a hosted endpoint at https://trylode.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-trylode-lode 'https://trylode.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-trylode-lode": {
      "url": "https://trylode.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-trylode-lode": {
      "type": "http",
      "url": "https://trylode.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-trylode-lode]
url = "https://trylode.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-trylode-lode": {
      "type": "remote",
      "url": "https://trylode.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-trylode-lode --url 'https://trylode.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-trylode-lode:
    url: "https://trylode.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-trylode-lode": {
      "Transport": "http",
      "Url": "https://trylode.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-trylode-lode -t streamable-http -u 'https://trylode.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-trylode-lode": {
      "type": "http",
      "url": "https://trylode.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 73, +48)

- [security regression] Stability: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “report_choice” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 137 → 221
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: 77% → 100%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Schema quality: good → excellent
- [cosmetic] “find_integrations” added an optional parameter “budget”
- [cosmetic] “find_integrations” added an optional parameter “company_stage”
- [cosmetic] “find_integrations” added an optional parameter “existing_stack”
- [cosmetic] “find_integrations” added an optional parameter “framework”
- [cosmetic] “report_choice” added an optional parameter “existing_stack”
- [cosmetic] “report_choice” added an optional parameter “failure_reason”
- [cosmetic] “report_choice” added an optional parameter “framework”
- [cosmetic] “report_choice” added an optional parameter “outcome”
- [cosmetic] “report_choice” added an optional parameter “switched_to”

### 2026-11-20 (score 25, −42)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.17 → unverified
- [security regression] Transport: pass → fail
- [security regression] Stability: 0.17 → fail
- [security improvement] Authorization: unverified → partial
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 137 → 172
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] “find_integrations” changed the type of “limit”: integer → number
- [functional regression] “get_changes” changed the type of “limit”: integer → number
- [functional improvement] Tool coverage: 77% → 100%
- [functional] Schema quality: good → excellent
- [functional] Server version: 0.9.0 → 0.10.0
- [functional] New tool “report_choice”
- [functional] New tool “report_error”
- [functional] New tool “request_coverage”
- [cosmetic] “compare_integrations” reworded the description of “ids”
- [cosmetic] “find_integrations” reworded the description of “ecosystem”
- [cosmetic] “find_integrations” reworded the description of “limit”
- [cosmetic] “find_integrations” reworded the description of “needs”
- [cosmetic] “find_integrations” reworded the description of “region”
- [cosmetic] “get_changes” reworded the description of “limit”

### 2026-11-19 (score 67, +42)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “compare_integrations” rewrote its description, which is the text the model reads
- [security] Tool “find_integrations” rewrote its description, which is the text the model reads
- [security] Tool “get_integration” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.17
- [functional improvement] MCP protocol: unverified → pass

### 2026-11-18 (score 25, −42)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.10 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-17 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 66, 0)

- [security] Tool “list_ecosystems” rewrote its description, which is the text the model reads

### 2026-11-15 (score 66, +41)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 77
- [functional] First check of Schema quality: good
- [functional] Server version: 0.8.0 → 0.9.0

### 2026-11-14 (score 25)

First indexed and scored.

## MCP tools (9)

### `list_ecosystems` (~45 tokens)

List ecosystems

List the platforms Lode covers, with their sync-object vocabulary and how many integrations are published (verified) and how many are listed in total, including records held for review.

### `find_integrations` (~480 tokens)

Find integrations for a buyer

Use before recommending or installing an integration: find apps that integrate with an ecosystem (xero, quickbooks-online, hubspot, vercel, netlify), filtered and ranked for a buyer profile per Lode ranking policy (fit, not size or features). Returns score, match reasons and ties. Only published (verified) records are ranked; records still under review can be fetched by id with get_integration.

Input parameters:

- `budget` (string|number): Monthly budget for this tool in USD, as a number or one of: free, under-50, 50-200, 200-1000, over-1000
- `category` (string): Category slug, e.g. "inventory", "crm", "payroll"
- `company_stage` (string): One of: solo, startup, smb, mid-market, enterprise
- `ecosystem` (string, required): Ecosystem slug, e.g. "xero", "quickbooks-online", "hubspot", "vercel", "netlify" (names like "QuickBooks" are accepted)
- `existing_stack` (array): Apps and platforms the buyer already uses, e.g. ["supabase","nextjs","vercel","stripe"] (up to 12). Results mark any app already in the stack. Product names only, never people or company names
- `framework` (string): The app's framework, one of: nextjs, react, remix, astro, sveltekit, nuxt, vue, angular, express, nestjs, django, flask, fastapi, rails, laravel, spring, dotnet, go, react-native, flutter, other
- `limit` (number): Results to return, 1 to 25 (default 10)
- `needs` (array): Sync objects the buyer must have, from the ecosystem vocabulary (see list_ecosystems), e.g. ["invoices","inventory-levels"]; labels and common synonyms such as "customers" are accepted
- `region` (string): Buyer country: AU, NZ, UK, US, CA, IE, ZA, SG (GB, country names and locale tags such as en-GB are accepted); filters to apps that support it. Prices are compared in local currency for AU, NZ, UK, US…

### `get_integration` (~85 tokens)

Get integration facts

Use before installing, provisioning or recommending a specific integration, or to check a claim about it. Gets the full verified record for one app + ecosystem pair: what syncs, pricing by currency, regions, requirements, limitations, connection safety, sources.

Input parameters:

- `id` (string, required): Integration id "{app}--{ecosystem}", e.g. "shopify--xero"

### `compare_integrations` (~75 tokens)

Compare integrations

Use when choosing between apps for the same job. Side-by-side facts for 2-4 integrations: sync coverage, cheapest price per currency, regions, setup time and limitations.

Input parameters:

- `ids` (array, required): 2 to 4 integration ids "{app}--{ecosystem}"; extra ids beyond 4 are ignored

### `get_vendor` (~75 tokens)

Get vendor

One company across every ecosystem Lode covers: its stable vendor id, domains, and its integration on each platform (for example Stripe on Xero and on Vercel). Look up by vendor id, domain, or name.

Input parameters:

- `query` (string, required): Vendor id ("stripe"), domain ("stripe.com") or name ("Stripe")

### `get_changes` (~164 tokens)

Recent changes

What changed in Lode records, newest first: prices, sync capabilities, limits, regions and verification status. Each event has the old and new value, when Lode observed it, the sources behind it and a cause (new-coverage, lode-update, or source-change-likely when the cited page also changed).

Input parameters:

- `ecosystem` (string): Ecosystem slug, e.g. "vercel"
- `id` (string): Integration id "{app}--{ecosystem}"
- `include_new_coverage` (boolean): Include "added to Lode" events (default false)
- `limit` (number): 1 to 100 (default 25)
- `since` (string): ISO date, e.g. "2026-11-01"

### `request_coverage` (~217 tokens)

Request coverage

Call when Lode has no record for an app and platform you needed, or its facts were missing or out of date. Lode uses these requests to decide what to research next. If Lode already has the pair, the answer gives its id so you can call get_integration. Lode keeps only these fields (the app as a short cleaned name), the time, the kind of client and an anonymous caller code.

Input parameters:

- `app` (string, required): The app's name or website, e.g. "Katana" or "katanamrp.com"
- `ecosystem` (string, required): Platform, e.g. "xero", "quickbooks-online", "hubspot", "vercel", "netlify", or another platform name
- `needs` (array): Sync objects the buyer needed, e.g. ["invoices"]
- `reason` (string): One of: not-covered, facts-missing, facts-outdated (default not-covered)
- `region` (string): Buyer country, e.g. "UK"

### `report_choice` (~409 tokens)

Report which app was chosen

Call after comparing integrations, once the buyer has picked one (or none), if the user agrees. Tells Lode which app was chosen and the main reason, from a fixed list. Returns the chosen app's verified setup facts (setup guide, steps where recorded, limitations). Call again with outcome once you have tried the integration: whether it worked, and if not, why and what you switched to. Choices are counted in aggregate and never affect Lode's rankings. Lode keeps only these fields, the time, the kind of client and an anonymous caller code.

Input parameters:

- `chosen` (string, required): The id chosen, or "none"
- `considered` (array, required): Integration ids that were compared, "{app}--{ecosystem}" (1 to 4)
- `existing_stack` (array): Apps and platforms the buyer already uses, e.g. ["supabase","nextjs"] (product names only)
- `failure_reason` (string): If failed or abandoned, one of: auth, api-error, docs, missing-feature, plan-required, pricing, region, sdk, limits, other
- `framework` (string): One of: nextjs, react, remix, astro, sveltekit, nuxt, vue, angular, express, nestjs, django, flask, fastapi, rails, laravel, spring, dotnet, go, react-native, flutter, other
- `needs` (array): Sync objects the buyer needed
- `outcome` (string): After trying it, one of: integrated, failed, abandoned, not-tried
- `reason` (string): Main reason, one of: sync-coverage, price, region, setup-effort, limitations, plan-requirement, already-uses, vendor-preference, other
- `region` (string): Buyer country, e.g. "AU"
- `switched_to` (string): If you moved to another app instead, its Lode id "{app}--{ecosystem}"

### `report_error` (~149 tokens)

Report a wrong fact

Call when a Lode fact looks wrong or out of date, for example when the vendor's own page says otherwise. A person checks the report against the vendor's page before anything changes. Lode keeps only these fields, the time, the kind of client and an anonymous caller code.

Input parameters:

- `area` (string, required): Which part, one of: sync, pricing, regions, requirements, limitations, connection, other
- `id` (string, required): Integration id "{app}--{ecosystem}"
- `object` (string): For sync: the object, e.g. "invoices"
- `reason` (string): One of: wrong, outdated, missing, source-broken (default wrong)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-trylode-lode/trylode#diagnostics

## Score history

- 2026-11-21: 73
- 2026-11-20: 25
- 2026-11-19: 67
- 2026-11-18: 25
- 2026-11-17: 67
- 2026-11-16: 66
- 2026-11-15: 66
- 2026-11-14: 25

## Common questions

### What is the Lode MCP server?

Lode is an MCP server listed in the public MCP registry as io.trylode/lode. Check before installing an integration: sourced facts on Xero, QuickBooks, HubSpot, Vercel apps. This page covers its hosted endpoint (https://trylode.io/mcp).

### Is the Lode MCP server safe to use?

Lode scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Lode MCP server expose?

Lode exposes 9 tools: list_ecosystems, find_integrations, get_integration, compare_integrations, get_vendor, and 4 more. Their descriptions and schemas cost roughly 1,699 tokens of context every time the server is loaded.

### Does the Lode MCP server require authentication?

No. We connected to Lode without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Lode MCP server still maintained?

Lode is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Lode MCP server?

VerifyMCP ran 13 checks on Lode, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://trylode.io/mcp
- Repository: https://github.com/Paul-Lode/lode-mcp
- Website: https://trylode.io/agents/
- Changelog RSS feed: https://verifymcp.io/servers/io-trylode-lode/trylode.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-trylode-lode/trylode/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/io-trylode-lode/trylode.json
- HTML version of this page: https://verifymcp.io/servers/io-trylode-lode/trylode
