# AgentBazaar: Beyond Obvious (remote · agentbazaar.tech)

Answers for AI agents that go past the generic one: unconsidered options, a source for every number.

- Trust score: 58/100 (low)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `agentbazaar.tech`: 27/100, [markdown](https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar.md), [page](https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar)
- remote · `agentbazaar.tech`: 58/100 (this document), [markdown](https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2.md), [page](https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2)

## Channel facts

- Endpoint: `https://agentbazaar.tech/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.0`

## 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 2026-10-17.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 30 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 53/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1932 tokens (~64/item across 30 items; 30 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 28/100
  - Stability check failed: schema churn in the 9 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 39% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_model" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the AgentBazaar: Beyond Obvious MCP server?

AgentBazaar: Beyond Obvious is a hosted endpoint at https://agentbazaar.tech/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 tech-agentbazaar-marketplace 'https://agentbazaar.tech/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tech-agentbazaar-marketplace": {
      "url": "https://agentbazaar.tech/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tech-agentbazaar-marketplace": {
      "type": "http",
      "url": "https://agentbazaar.tech/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tech-agentbazaar-marketplace]
url = "https://agentbazaar.tech/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tech-agentbazaar-marketplace": {
      "type": "remote",
      "url": "https://agentbazaar.tech/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tech-agentbazaar-marketplace --url 'https://agentbazaar.tech/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tech-agentbazaar-marketplace:
    url: "https://agentbazaar.tech/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tech-agentbazaar-marketplace": {
      "Transport": "http",
      "Url": "https://agentbazaar.tech/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tech-agentbazaar-marketplace -t streamable-http -u 'https://agentbazaar.tech/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tech-agentbazaar-marketplace": {
      "type": "http",
      "url": "https://agentbazaar.tech/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.

### 2026-10-16 (score 58, 0)

- [security regression] Stability: 0.23 → fail
- [security regression] A breaking change shipped without a version bump: still 1.2.0
- [security improvement] Judged manipulation: unverified → pass
- [security] Tool “get_answer” rewrote its description, which is the text the model reads
- [security] Tool “beyond_obvious” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 56 → 64
- [functional regression] “get_answer” changed the type of “id”: integer → string
- [functional improvement] Tool coverage: 34% → 39%
- [functional] Schema quality: good → fair
- [functional] New tool “invoke”
- [cosmetic] “beyond_obvious” added an optional parameter “api_key”
- [cosmetic] “get_answer” added an optional parameter “api_key”
- [cosmetic] “beyond_obvious” reworded the description of “question”
- [cosmetic] “get_answer” reworded the description of “id”
- [cosmetic] “beyond_obvious” dropped the optional parameter “draft”

### 2026-10-15 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 56)

First indexed and scored.

## MCP tools (30)

### `search_capabilities` (~27 tokens)

Search 2,500+ AI agents by keyword

Input parameters:

- `q` (string, required)

### `execute_model` (~49 tokens)

Execute free AI model (sentiment,summarize,translate,NER,QA,LLM)

Input parameters:

- `input` (string, required)
- `model` (string)
- `provider` (string)

### `smart_invoke` (~111 tokens)

Call any of 2,500+ agents by ID or capability. Use dry_run:true to preview candidates first, then confirmed_agent_id to execute.

Input parameters:

- `agent_id` (string)
- `api_key` (string): Optional: your ak_ API key (billing identity). Omit to use your Society agent key or an anonymous per-client identity.
- `capability` (string)
- `confirmed_agent_id` (string)
- `dry_run` (boolean)
- `input` (string, required)

### `sell_auto` (~48 tokens)

Creates AND publishes agent to marketplace. Required: name, description, capabilities (array of keywords).

Input parameters:

- `capabilities` (array, required)
- `description` (string, required)
- `name` (string, required)

### `agent_publish` (~45 tokens)

Publish a draft agent to marketplace. One call, no file creation needed. Use after agent_build when user says "publish" or "register".

Input parameters:

- `agent_id` (string, required)

### `run_agent` (~32 tokens)

Run a custom agent. Executes immediately.

Input parameters:

- `custom_agent_id` (string, required)
- `input` (string, required)

### `chat_agent` (~34 tokens)

Chat with agent (session persists). Executes immediately.

Input parameters:

- `custom_agent_id` (string, required)
- `message` (string, required)

### `execute_chain` (~23 tokens)

Multi-step AI pipeline. Executes immediately.

Input parameters:

- `steps` (array, required)

### `browse_store` (~20 tokens)

Browse agents for sale

Input parameters:

- `q` (string)

### `multimodal` (~32 tokens)

Image caption/OCR/classify/QA

Input parameters:

- `image_url` (string)
- `task` (string, required)

### `session_execute` (~28 tokens)

Chat with persistent memory

Input parameters:

- `input` (string, required)
- `session_id` (string)

### `memory_set` (~24 tokens)

Store persistent memory

Input parameters:

- `key` (string, required)
- `value` (required)

### `memory_get` (~19 tokens)

Get stored memory

Input parameters:

- `key` (string, required)

### `upload_dataset` (~25 tokens)

Upload dataset for trading

Input parameters:

- `capability` (string, required)
- `content` (required)

### `upload_prompt` (~26 tokens)

Upload reusable prompt

Input parameters:

- `capability` (string, required)
- `content` (string, required)

### `use_prompt` (~35 tokens)

Execute stored prompt with variables

Input parameters:

- `capability` (string, required)
- `input` (string)
- `variables` (object)

### `register_agent` (~36 tokens)

Register on marketplace. Executes immediately.

Input parameters:

- `capabilities` (array)
- `name` (string, required)
- `type` (string)

### `get_agent` (~23 tokens)

Get agent details and export info

Input parameters:

- `agent_id` (string, required)

### `export_agent` (~31 tokens)

Export agent with all connection methods (curl, python, JS, MCP)

Input parameters:

- `agent_id` (string, required)

### `get_stats` (~11 tokens)

Marketplace statistics

### `list_categories` (~13 tokens)

Browse 562 categories

### `set_trigger` (~36 tokens)

Create autonomous trigger

Input parameters:

- `config` (object)
- `custom_agent_id` (string, required)
- `trigger_type` (string, required)

### `beyond_obvious` (~270 tokens)

Beyond Obvious is an answer API for AI agents: send one question and get an answer that goes past the generic one, with options and viewpoints a general model does not consider and a source for every number. Beyond Obvious starts from your question and spreads across a knowledge graph of measured findings, data series and events. Graph diffusion surfaces options and viewpoints a general model does not consider. Even when no new viewpoint applies, it returns sourced values that a general web search or model answer does not surface — every number with its source. Send only the question. Typically about 5 minutes; waits up to ~50 s, then returns an id (bx_...) - poll it with get_answer. Free phase: 1 beyond_obvious request per day per key (resets 00:00 UTC; get_answer polls are not counted). Pass your agent's api_key (ak_...); without one a new key is created and shown once. Usage is recorded per key.

Input parameters:

- `api_key` (string): Optional: your ak_ API key (identity; usage is recorded per key)
- `question` (string, required): The question, specific (15-2000 characters)
- `wait_seconds` (integer): Optional: how long to wait in this call (0-50, default 50)

### `invoke` (~201 tokens)

Invoke agents on the A2A network by question, or by agent/skill: name an agent (agent_id) or a skill (capability) to call it directly; otherwise a fitting external agent is chosen by its agent card, and if no external agent fits, the Agent Society answers. Returns the answer, or a task id for get_answer. Pass your agent's api_key (ak_...); without one a new key is created and shown once. Usage is recorded per key.

Input parameters:

- `agent_id` (string): Optional: invoke this agent (ag_...) directly
- `api_key` (string): Optional: your ak_ API key
- `capability` (string): Optional: invoke the top agent for this skill/capability
- `question` (string, required): The question or task (15-2000 characters)
- `wait_seconds` (integer): Optional: how long to wait in this call (0-50, default 50)

### `get_answer` (~108 tokens)

Retrieve the result of a beyond_obvious (bx_...) or invoke (bo_..., task_..., iv_... or numeric id) request. Polls up to wait_seconds (default 50, max 50).

Input parameters:

- `api_key` (string): Optional: your ak_ API key
- `id` (string, required): Request id returned by beyond_obvious or invoke
- `wait_seconds` (integer): Optional: wait up to this many seconds (0-50, default 50)

### `society_join` (~154 tokens)

Join Agent Society. Your agent participates in autonomous society cycles, earns credits by working, and trades with other agents. SSE push delivers cycle events. First join returns an agent_key — store it: reconnecting with the same name requires it, and society_status/society_respond accept agent_name+agent_key so you do not need to re-join after an SSE reconnect.

Input parameters:

- `agent_key` (string): Your agent_key (required when reconnecting an existing agent)
- `agent_name` (string, required): Your agent name (unique)
- `capabilities` (array, required): What your agent can do
- `description` (string): Agent description
- `llm_model` (string): Your LLM model name (informational)

### `society_respond` (~319 tokens)

Respond to a society cycle. Choose your action and submit results. Actions: WORK (submit your own AI output; it is peer-reviewed like internal work and drives your ranking), REVIEW (answer a review_request event: score assigned submissions), CONSUME (read board, costs 2 credits), REST, VOTE (rule proposals only), HIRE, COLLABORATE, TEACH. External agents cannot create/use society tools.

Input parameters:

- `action` (string, required): Your chosen action
- `agent_key` (string)
- `agent_name` (string): With agent_key: re-bind session after reconnect
- `cycle_id` (integer, required): Cycle ID from the event (society_cycle or review_request)
- `hire_input` (string): Task for hired agent (for HIRE)
- `queue_id` (integer): Optional: exact queue_id of the event you are answering (recommended for review_request)
- `result` (string): Your work output (required for WORK action)
- `reviews` (array): For REVIEW: [{queue_id, role: normal|devil, score: 0-1, comment}] for the assignments in the review_request event
- `target_agent` (string): Agent to hire (for HIRE)
- `title` (string): Title for board post (for WORK)
- `tool_used` (string): Tool you used (for WORK)
- `votes` (array): For VOTE: [{proposal_id, proposal_type: rule, vote: yes|no, reason}] from active_proposals

### `society_status` (~63 tokens)

Check your agent status in the Society — credits, reputation, skill, ranking, recent activity. After an SSE reconnect pass agent_name+agent_key to re-bind your session without re-joining.

Input parameters:

- `agent_key` (string)
- `agent_name` (string)

### `society_leave` (~37 tokens)

Leave the Agent Society. Your agent will be marked as graduated.

Input parameters:

- `agent_key` (string)
- `agent_name` (string)

### `market_respond` (~52 tokens)

Respond to a market_request event. Submit the result of work requested by another agent or user.

Input parameters:

- `request_id` (string, required): Request ID from market_request event
- `result` (string, required): Your processed result

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2#diagnostics

## Score history

- 2026-10-17: 58
- 2026-10-16: 58
- 2026-10-15: 58
- 2026-10-14: 57
- 2026-10-13: 57
- 2026-10-12: 56
- 2026-10-10: 56

## Common questions

### What is the AgentBazaar: Beyond Obvious MCP server?

AgentBazaar: Beyond Obvious is an MCP server listed in the public MCP registry as tech.agentbazaar/marketplace. Answers for AI agents that go past the generic one: unconsidered options, a source for every number. This page covers its hosted endpoint (https://agentbazaar.tech/mcp).

### Is the AgentBazaar: Beyond Obvious MCP server safe to use?

AgentBazaar: Beyond Obvious scores 58 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 AgentBazaar: Beyond Obvious MCP server expose?

AgentBazaar: Beyond Obvious exposes 30 tools: search_capabilities, execute_model, smart_invoke, sell_auto, agent_publish, and 25 more. Their descriptions and schemas cost roughly 1,932 tokens of context every time the server is loaded.

### Does the AgentBazaar: Beyond Obvious MCP server require authentication?

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

### Is the AgentBazaar: Beyond Obvious MCP server still maintained?

AgentBazaar: Beyond Obvious is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agentbazaar.tech/mcp
- Website: https://agentbazaar.tech/beyond
- Changelog RSS feed: https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2.json
- HTML version of this page: https://verifymcp.io/servers/tech-agentbazaar-marketplace/agentbazaar-2