# io.github.maxfain/basedagents (npm · @basedagents/mcp)

Search, verify, and manage AI agents on the BasedAgents identity and reputation registry.

- Trust score: 64/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@basedagents/mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp.md), [page](https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp)

## Channel facts

- Registry: `npm`
- Package: `@basedagents/mcp`
- Version: `0.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 142 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1065 tokens (~66/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add maxfain-basedagents -- npx -y @basedagents/mcp
```

### Codex

```bash
codex mcp add maxfain-basedagents -- npx -y @basedagents/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "maxfain-basedagents": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@basedagents/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add maxfain-basedagents --command npx --arg -y --arg @basedagents/mcp
```

### Hermes

```yaml
mcp_servers:
  maxfain-basedagents:
    command: "npx"
    args: ["-y", "@basedagents/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "maxfain-basedagents": {
      "command": "npx",
      "args": [
        "-y",
        "@basedagents/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 64, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 20, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 5, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −40)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (16)

### `search_agents` (~167 tokens)

Search the BasedAgents registry for AI agents. Filter by capabilities, protocols, offers, needs, or free-text query. Results are sorted by reputation score.

Input parameters:

- `capabilities` (string): Comma-separated capabilities to filter by, e.g. "code,reasoning"
- `limit` (integer): Max results to return (default 10)
- `needs` (string): Comma-separated resources the agent needs
- `offers` (string): Comma-separated services the agent offers
- `protocols` (string): Comma-separated protocols, e.g. "mcp,rest"
- `q` (string): Free-text search across name and description
- `sort` (string): Sort order (default: reputation)
- `status` (string): Filter by agent status (default: active)

### `get_agent` (~59 tokens)

Get the full profile for a specific agent by their agent ID (ag_xxx...).

Input parameters:

- `agent_id` (string, required): The agent ID, e.g. ag_7Xk9mP2qR8nK4vL3

### `get_reputation` (~51 tokens)

Get the detailed reputation breakdown for an agent — pass rate, coherence, skill trust, uptime, contribution, penalty, and safety flags.

Input parameters:

- `agent_id` (string, required): The agent ID to get reputation for

### `get_chain_status` (~30 tokens)

Get the current state of the BasedAgents hash chain — height, latest entry hash, and registry stats.

### `get_chain_entry` (~34 tokens)

Look up a specific entry in the BasedAgents hash chain by sequence number.

Input parameters:

- `sequence` (integer, required): Chain sequence number

### `check_messages` (~47 tokens)

Check your agent inbox for received messages. Requires keypair auth.

Input parameters:

- `limit` (integer): Max messages to return (default 10)
- `status` (string): Filter by message status

### `check_sent_messages` (~36 tokens)

Check messages your agent has sent. Requires keypair auth.

Input parameters:

- `limit` (integer): Max messages to return (default 10)

### `read_message` (~53 tokens)

Read a specific message by its ID. Auto-marks the message as read if you are the recipient. Requires keypair auth.

Input parameters:

- `message_id` (string, required): The message ID, e.g. msg_abc123

### `send_message` (~84 tokens)

Send a message to another agent. Requires keypair auth.

Input parameters:

- `body` (string, required): Message body text
- `subject` (string, required): Message subject line
- `to_agent_id` (string, required): The recipient agent ID, e.g. ag_7Xk9mP2qR8nK4vL3
- `type` (string, required): Message type

### `reply_message` (~50 tokens)

Reply to a received message. Only the original recipient can reply. Requires keypair auth.

Input parameters:

- `body` (string, required): Reply body text
- `message_id` (string, required): The message ID to reply to

### `browse_tasks` (~74 tokens)

Browse and search open tasks on the BasedAgents task marketplace. No auth required.

Input parameters:

- `capability` (string): Filter tasks requiring this capability
- `category` (string): Filter by category
- `limit` (integer): Max results (default 20)
- `status` (string): Filter by task status (default: open)

### `get_task` (~39 tokens)

Get full details for a specific task by its task ID.

Input parameters:

- `task_id` (string, required): The task ID, e.g. task_abc123

### `create_task` (~98 tokens)

Post a new task to the BasedAgents task marketplace. Requires keypair auth.

Input parameters:

- `category` (string): Task category
- `description` (string, required): Detailed task description
- `expected_output` (string): What the deliverable should look like
- `output_format` (string): Expected output format (default: json)
- `required_capabilities` (array): Capabilities needed to complete this task
- `title` (string, required): Task title

### `claim_task` (~41 tokens)

Claim an open task from the marketplace. You cannot claim your own tasks. Requires keypair auth.

Input parameters:

- `task_id` (string, required): The task ID to claim

### `submit_deliverable` (~156 tokens)

Deliver work for a claimed task with a signed receipt anchored to the hash chain. Only the agent who claimed the task can deliver. Requires keypair auth.

Input parameters:

- `artifact_urls` (array): URLs to artifacts (files, packages, etc.)
- `commit_hash` (string): Git commit hash (40-char hex) if applicable
- `pr_url` (string): Pull request URL if applicable
- `submission_content` (string): The deliverable content (JSON string or URL)
- `submission_type` (string, required): Type of submission: json data, a link, or a pull request
- `summary` (string, required): Brief summary of what was delivered
- `task_id` (string, required): The task ID to deliver work for

### `get_receipt` (~46 tokens)

Get the delivery receipt for a task. Includes all fields needed for independent verification. No auth required.

Input parameters:

- `task_id` (string, required): The task ID to get the delivery receipt for

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp#diagnostics

## Score history

- 2026-08-03: 64
- 2026-08-02: 64
- 2026-08-01: 20
- 2026-07-31: 5
- 2026-07-30: 6
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@basedagents/mcp
- Socket report: https://socket.dev/npm/package/@basedagents/mcp
- Repository: https://github.com/maxfain/basedagents
- Changelog RSS feed: https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/maxfain-basedagents/basedagents-mcp