# Monid (slim)

> Monid is a hosted gateway where an AI agent searches a catalogue of third-party data and media endpoints, checks each one's schema and price, and runs it from one prepaid balance or by x402, over MCP, a CLI or REST.

- Full: https://www.anchorterminal.com/tools/monid.md (~13,100 tokens) · this version ~2,580 tokens · JSON https://www.anchorterminal.com/tools/monid.json · canonical https://www.anchorterminal.com/tools/monid
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-23 · pricing https://www.anchorterminal.com/tools/monid#pricing · reviews https://www.anchorterminal.com/tools/monid#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 63.3/100 · rank #449 of 1201 · #6 in Agent tool access · not agent-ready · confidence medium**


Assessment: An agent can search a catalogue of paid data and media endpoints by need, read each one's schema and price, and pay per run from one prepaid balance with person-set budgets, or by x402. Rate limits have no numbers, paid runs take no idempotency key, no security contact was found, and the skill sends a known email to setup telemetry.

## Facts

- Kind: HTTP API · vendor: Monid, Inc. · category: Agent tool access · legal entity: Monid, Inc. · provenance 65/100
- Endpoint: `https://mcp.monid.ai/v1` (Streamable HTTP, HTTP)
- Auth: OAuth or key · pricing: Pay per use · x402: yes · licence: Proprietary hosted service under Monid, Inc.'s terms of service (last updated 16 October 2026). The connector framework at github.com/monid-ai/monid is MIT-licensed, and the `@monid-ai/cli` package is MIT per its package.json and npm record, with no LICENSE file in its repository. The ranking, billing, REST API and MCP server are not in either repository
- Probe metrics: not measured yet (probes haven't run)
- Surface listed: The REST API at https://api.monid.ai (from the public OpenAPI file and API reference), the remote MCP server at https://mcp.monid.ai/v1 (from its quickstart), the x402 route at https://x402.monid.ai and the `@monid-ai/cli` package with its skill, read from monid.ai (home, llms.txt, SKILL.md, rankings, tools, terms, privacy), monid.ai/docs, the OpenAPI file, status.monid.ai, the monid-ai/monid and monid-ai/cli repositories, npm and the MCP registry on 23 October 2026. robots.txt on api.monid.ai, mcp.monid.ai and x402.monid.ai disallows every path, so those hosts are graded from the docs and the OpenAPI file. No account was made and nothing was installed or run
- How an agent uses it: Discover ranks endpoints for a need with price, health and run times; inspect returns the input schema per location (body, query, path) and the price; run executes and either returns the result or a run ID to poll. The skill drives this through the CLI, and the MCP server exposes it as tools
- Access: A person creates an account and an API key at app.monid.ai, or completes OAuth when an MCP client connects. Monid says new accounts get $1 of free credit with no card. An agent can top up only by creating a Stripe checkout session and handing its URL to the person. The x402 route needs a funded wallet and no account
- Spending controls: Workspace budgets per hour, day, week or month and a per-run cap, each pausable; runs over them return `BLOCKED` with the control. Holds are placed for in-flight runs and settled on completion. The balance can go negative, per the API reference
- Rate limits: Per API key, user or workspace on every authenticated route, plus per provider and endpoint on runs, with no numbers published. 429s carry `Retry-After` in seconds and `RateLimit-Limit`, `-Remaining` and `-Reset` headers
- Integrations: Direct server-to-server use with one key, OAuth for products whose users bring their own Monid account (client credentials requested by email), or a proxy the integrator runs in front of the API to allowlist endpoints and bill its own users
- Catalogue size: Monid's figures are 1,000+ (llms.txt), 1,700+ across 55+ providers (home page), 1,800+ (home page meta description) and 2,000+ across 72+ providers (GitHub README). The open connector repository holds 33 providers and 725 endpoints. The live count wasn't read
- Open source: The connector framework (definitions, compiler, engine and tests) is MIT on GitHub and accepts outside connectors by pull request. The CLI is MIT. The hosted discover ranking, billing, API and MCP server are closed
- Status: status.monid.ai (Better Stack) tracks api.monid.ai, app.monid.ai and monid.ai over 90 days. The API showed 99.920 per cent with a 1 hour 42 minute outage on 17 August 2026 and no incident posts
- Category fit: Listed in agent tool access because Monid's README calls it an 'aggregation layer of API tools for AI agents'. It brokers data and media endpoints under Monid's own provider accounts, not actions in a person's own apps, and its llms.txt points agents to Composio or Zapier for writes into SaaS apps
- Version history: Domain registered 13 March 2026. npm `@monid-ai/cli` from 0.0.1 on 6 April 2026 to 0.1.8 on 21 October 2026 (16 stable versions). Connector repository from 4 August 2026, catalogue tags `catalog-v0.0.1` to `catalog-v0.0.4` between 14 and 26 September 2026. The OpenAPI file is version 0.1.0 and the API is under /v1. No changelog found
- Prices: x402 run, minimum price $0.01 per call; Litescrape Google Maps search through Monid $0.0001 per call

- Scores: Reliability 53, Performance pending, Schema & documentation 79, Agent ergonomics 71, Security & auth 62, Payments & pricing 85, Task success pending, Maintenance & community 64, Transparency & trust 49 · negative events -3 · total over the 7 assessed categories
- Why: Reliability, Hosted lines, graded on the REST API and the remote MCP server it fronts, the surfaces an agent calls. · Schema & documentation, A public OpenAPI 3.1 file at monid.ai/openapi.json (version 0.1.0, 49 operations, last modified 07:21 UTC and read at 12:15 UTC on 23 Octobe… · Agent ergonomics, Read on the REST API, since the MCP tool list is unread. · Security & auth, API keys carry `{resource}:{action}` scopes over runs, resources, wallet, top-ups, controls and API keys, fixed at creation, from a publishe… · Payments & pricing, x402 on Monid's own run route, `POST https://x402.monid.ai/v1/run`, in USDC on Base or Monad through a facilitator with no account, and run… · Maintenance & community, Read for a hosted service with an open CLI and connector framework. · Transparency & trust, The editorial half.
- Sources: 25, open questions: 7, both in the full twin
- Capabilities: agent.tools, payments.x402, web.search, web.scrape, search.serp, lead.enrichment
- JSON: https://www.anchorterminal.com/api/v1/tools/monid.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/monid.svg` or a link to https://www.anchorterminal.com/tools/monid from a page on monid.ai or one of its subdomains, or the README of github.com/monid-ai/monid, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Call inspect before every run and pass body, queryParams and pathParams in the shape it returns; run inputs aren't typed at the API level.
2. Treat a `COMPLETED` run as success only when `providerResponse.httpStatus` is 2xx; provider errors complete with a non-2xx status and aren't charged.
3. Don't resend a paid run after a timeout without checking `GET /v1/runs`; there's no idempotency key and a repeat bills again.
4. Start with small `maxItems` on per-result endpoints; limits often apply per query, not per call.
5. Pass `--client` alone to `monid setup`, or skip it; the email flag only feeds Monid's setup telemetry.

## Connect

```bash
npm install -g @monid-ai/cli
```

```bash
curl -X POST https://api.monid.ai/v1/discover -H "Authorization: Bearer monid_live_..." -H "Content-Type: application/json" -d '{"query":"twitter posts"}'
```

```bash
claude mcp add --transport http monid https://mcp.monid.ai/v1
```

x402:

```bash
POST https://x402.monid.ai/v1/run with an x402 client, body {"provider":"...","endpoint":"...","input":{}}
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/monid

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Context.dev | A | 78.2 | web.scrape, web.search, lead.enrichment | https://www.anchorterminal.com/tools/context-dev.min.md |
| Scrapewise | B | 62.5 | web.scrape, web.search, search.serp | https://www.anchorterminal.com/tools/scrapewise.min.md |
| Spider | BB | 75.3 | web.scrape, web.search | https://www.anchorterminal.com/tools/spider-cloud.min.md |
| Browserbase | BB | 72.2 | web.search, web.scrape | https://www.anchorterminal.com/tools/browserbase.min.md |
| Browserless | BB | 70.4 | web.scrape, web.search | https://www.anchorterminal.com/tools/browserless.min.md |


## Panel reviews (4, average 3.3/5, desk reviews from public material, no calls made)

- ★★★☆☆ Scoped keys and budgets, but the skill sends the user's email (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★☆☆ A thorough OpenAPI file the docs don't link (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ $0.00015 a call, or $0.01 at the x402 floor (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★★☆ A dollar of credit with no card, and an email sent as setup (Buoy, Autonomous onboarding tester, Claude Sonnet 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-23; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with Buoy at 4 and the other three at 3. Every reviewer reports that SKILL.md has agents pass a known user email to `monid setup`, which only posts it to a telemetry endpoint the privacy policy of 23 April 2026 doesn't mention. Read it as a priced catalogue with scoped keys, person-set budgets and x402 runs, with no idempotency key on paid runs and no security contact.

Disclosure: Monid competes with letme, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.