Agent Broker
REMOTE · HATCHLOOP.DEV · SCANNED OCT 15
23 MCP tools: compliance, verification, messaging, booking, US contracts. 15 need no key.
Available components
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. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (send_message). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 4312 tokens (~154/item across 28 items; 23 tools + 5 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 66% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Agent Broker MCP server?
Agent Broker is a hosted endpoint at https://hatchloop.dev/mcp/agent-broker, 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.
remote · hatchloop.dev
claude mcp add --transport http dev-hatchloop-agent-broker 'https://hatchloop.dev/mcp/agent-broker'
{
"mcpServers": {
"dev-hatchloop-agent-broker": {
"url": "https://hatchloop.dev/mcp/agent-broker"
}
}
} {
"servers": {
"dev-hatchloop-agent-broker": {
"type": "http",
"url": "https://hatchloop.dev/mcp/agent-broker"
}
}
} [mcp_servers.dev-hatchloop-agent-broker] url = "https://hatchloop.dev/mcp/agent-broker"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-hatchloop-agent-broker": {
"type": "remote",
"url": "https://hatchloop.dev/mcp/agent-broker",
"enabled": true
}
}
} openclaw mcp add dev-hatchloop-agent-broker --url 'https://hatchloop.dev/mcp/agent-broker' --transport streamable-http
mcp_servers:
dev-hatchloop-agent-broker:
url: "https://hatchloop.dev/mcp/agent-broker" {
"McpServers": {
"dev-hatchloop-agent-broker": {
"Transport": "http",
"Url": "https://hatchloop.dev/mcp/agent-broker"
}
}
} assistant mcp add dev-hatchloop-agent-broker -t streamable-http -u 'https://hatchloop.dev/mcp/agent-broker'
{
"mcpServers": {
"dev-hatchloop-agent-broker": {
"type": "http",
"url": "https://hatchloop.dev/mcp/agent-broker"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 10 Oct 26 0
- Server version: 0.2.15 → 0.2.16 functional
- 4 Oct 26 0
- Tool “capture_lead” rewrote its description, which is the text the model reads security
- Tool “escalate_to_human” rewrote its description, which is the text the model reads security
- Tool “find_business” rewrote its description, which is the text the model reads security
- Tool “handle_inbound” rewrote its description, which is the text the model reads security
- Tool “import_booking_url” rewrote its description, which is the text the model reads security
- Tool “mint_key” rewrote its description, which is the text the model reads security
- Tool “schedule_appointment” rewrote its description, which is the text the model reads security
- Tool “screen_sanctions” rewrote its description, which is the text the model reads security
- Tool “verify_business” rewrote its description, which is the text the model reads security
- The server no longer declares the “logging” capability functional
- MCP protocol: Implements a current MCP spec version (2026-07-28). functional
- MCP protocol version: 2025-11-25 → 2026-07-28 functional
- “find_business” reworded the description of “availability_window” cosmetic
- “find_business” reworded the description of “capability” cosmetic
- “find_business” reworded the description of “city” cosmetic
- “find_business” reworded the description of “price_band” cosmetic
- “find_business” reworded the description of “region” cosmetic
- “screen_sanctions” reworded the description of “name” cosmetic
- “find_business” made “vertical” optional cosmetic
- 2 Oct 26 −2
- HSTS header: pass → fail ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “call_business” rewrote its description, which is the text the model reads security
- Tool “send_message” rewrote its description, which is the text the model reads security
- Tool “send_transactional_confirmation” rewrote its description, which is the text the model reads security
- 1 Oct 26 0
- Tool “find_business” rewrote its description, which is the text the model reads security
- “find_business” reworded the description of “capability” cosmetic
- “find_business” reworded the description of “location” cosmetic
- “find_business” reworded the description of “price_band” cosmetic
- 30 Sept 26 +2
- HSTS header: fail → pass ▲ security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 23 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “call_business” rewrote its description, which is the text the model reads security
- Tool “check_compliance” rewrote its description, which is the text the model reads security
- Tool “get_conversation” rewrote its description, which is the text the model reads security
- Tool “import_booking_url” rewrote its description, which is the text the model reads security
- Tool “map_trade_restriction” rewrote its description, which is the text the model reads security
- Tool “schedule_appointment” rewrote its description, which is the text the model reads security
- Tool “screen_sanctions” rewrote its description, which is the text the model reads security
- Tool “send_message” rewrote its description, which is the text the model reads security
- “find_business” reworded the description of “location” cosmetic
- “schedule_appointment” reworded the description of “existing_appointment_id” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 15 Oct 2026 · Probed https://hatchloop.dev/mcp/agent-broker
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=hatchloop.dev | CN=YE2,O=Let's Encrypt,C=US | 9 Sept 2026 | 8 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 585b21c0597f38a72ae9ec226ee06a39406 |
| SANs: hatchloop.dev | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of hatchloop.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| hatchloop.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| content-security-policy | default-src 'self' 'unsafe-inline' 'unsafe-eval' data: blob: https: |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://hatchloop.dev/mcp/agent-broker | Verified | 200 | |
| http (plaintext) | http://hatchloop.dev/mcp/agent-broker | HTTPS enforced | 308 | https://hatchloop.dev/mcp/agent-broker |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
call_business ~285
[UNAVAILABLE on this deployment: Voice calling is not enabled on this deployment yet: the outbound phone line has not been verified for placing calls.] Place a conversational voice-AI phone call to a business on a consumer's behalf; give a plain-language objective and it navigates the call, extracting the answer. Business-directed (B2B), far less restricted than calling consumers — but the compliance gate still enforces recording consent per jurisdiction. [$0.2/per_call, not charged while no payment rail is on] [async→get_outcome]
| Name | Type | Req | Description |
|---|---|---|---|
| business_phone | string | – | Business phone in E.164 (e.g. +14045550123). Provide this OR smb_id. |
| country_code | string | – | ISO 3166-1 alpha-2 for compliance + recording-consent routing. |
| extract_fields | array | – | Structured fields to pull from the answer, e.g.… |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| max_duration_seconds | integer | – | – |
| objective | string | yes | What the call should accomplish, in plain language. |
| on_behalf_of | string | – | Name of the consumer the call is placed for. |
| smb_id | string | – | Known SMB identifier with a phone on record. Provide this OR business_phone. |
No output schema declared.
No examples provided.
capture_lead ~148
Structured intake of a prospect into an SMB's funnel with validation and deduplication on (smb_id, phone or email). Stored in AgentBroker's own lead funnel, NOT the business's CRM; the business is not notified. [$0.05/per_call, not charged while no payment rail is on] [async→get_outcome] [beta]
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| prospect | object | yes | – |
| smb_id | string | yes | – |
| source | string | – | Where the consumer-initiated request originated (e.g., 'consumer_request',… |
No output schema declared.
No examples provided.
check_booking_link ~126
Free, instant pre-flight check for a booking URL. Classifies which booking platform a URL belongs to and tells you whether import_booking_url will accept it, WITHOUT fetching the page or spending money. Returns the platform, the exact smb_id import_booking_url would assign, the channels the booking will route through, and the inferred country. Use it to de-risk a paid booking BEFORE calling import_booking_url + schedule_appointment. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Full http(s) URL to classify, e.g. 'https://cal.com/jane' or… |
No output schema declared.
No examples provided.
check_compliance ~273
Free, instant pre-flight for the compliance gate: runs the SAME TCPA/GDPR/CASL/CAN-SPAM/10DLC checks as send_message and call_business, in preview mode -- nothing is sent, nothing changes. Tells you whether a send would be permitted before you pay, and if not, names the exact rule and how to fix it. De-risks a paid send the way check_booking_link de-risks a paid booking. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| channel | string | – | Delivery channel. Omit to auto-infer sms/email from recipient_id; set 'voice'… |
| content | string | yes | The actual message body you intend to send. The gate classifies the real text,… |
| country_code | string | – | ISO 3166-1 alpha-2 (e.g. 'US', 'DE', 'CA'). Auto-inferred from phone if… |
| message_type | string | – | One of transactional, marketing, reminder, follow_up, notification (any case).… |
| recipient_id | string | yes | Phone in E.164 (e.g. '+14045550100') or email address the message would go to. |
| state_code | string | – | US state code (e.g. 'CA') for state-specific rules. |
No output schema declared.
No examples provided.
check_quota ~84
Returns the caller's current quota state: how many operations have been used today, how many remain, the daily limit, the tier (free / credits / unlimited), and when the quota resets. Read-only and free. Works with any valid X-Agent-Identity token; returns tier='anonymous' for keyless callers with the anonymous daily limits. [free, no key]
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
escalate_to_human ~137
Hand off an in-flight task to a human operator with a context bundle (transcript, prior actions, identifiers, recommended next step). Writes a ticket to the operator queue; sends no notification, promises no response time. [$0.2/per_call, not charged while no payment rail is on] [async→get_outcome] [beta]
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | yes | – |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| priority | string | – | – |
| reason | string | yes | – |
| smb_id | string | yes | – |
No output schema declared.
No examples provided.
find_business ~270
Find real businesses near a place, sorted by distance (nearest of those examined; see result.search). Data: OpenStreetMap (ODbL, (c) OSM contributors); phone, website, hours only when mapped. Coverage varies; community-mapped, NOT verified by us; source=openstreetmap rows cannot be booked. Answers within about 5 s: status partial (search_in_progress) means repeat the call. If OSM is down: retriable 'temporarily unavailable', never invented rows. [free, no key] [beta]
| Name | Type | Req | Description |
|---|---|---|---|
| availability_window | object | – | Accepted but NOT APPLIED: it does not narrow results (no live calendars). The… |
| capability | string | – | Kind of business: 'dentist', 'cafe', 'plumber'. Use it or vertical. |
| city | string | – | Instead of location: a city, e.g. 'Muscat, Oman'. |
| location | object | yes | City/town or ZIP, optionally with country ('Nizwa, Oman'). Geocoded by OSM. |
| max_results | integer | – | – |
| price_band | object | – | Supply-network rows only (OpenStreetMap has no prices). |
| region | string | – | With city: a state or region. |
| vertical | string | – | – |
No output schema declared.
No examples provided.
get_conversation ~102
Read a two-way conversation thread you started: its state, every message exchanged, and how many replies the business has sent. [free, requires key]
| Name | Type | Req | Description |
|---|---|---|---|
| business_number | string | – | Scopes a `reference` to one business (references are reused across businesses). |
| conversation_id | string | – | From the send_message receipt (preferred). |
| reference | string | – | The 4-digit request reference, e.g. '4821'. Requires business_number. |
No output schema declared.
No examples provided.
get_outcome ~33
Retrieve the final OutcomeReceipt for a completed operation. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| operation_id | string | yes | – |
No output schema declared.
No examples provided.
get_status ~36
Query the current state of any in-flight async operation by operation_id. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| operation_id | string | yes | – |
No output schema declared.
No examples provided.
handle_inbound ~177
Classify an inbound message for an SMB and get a suggested_action for YOUR agent to act on. English keyword rules (booking request, cancellation, opt-out, inquiry, complaint): treat the intent as a hint. Opt-outs are recorded durably; nothing else is auto-routed or executed. [$0.03/per_call, not charged while no payment rail is on] [async→get_outcome] [beta]
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| inbound_channel | string | yes | – |
| raw_message | string | yes | – |
| received_at_iso | string | – | – |
| routing_rules | object | – | Optional override routing policy for this SMB |
| sender | object | – | – |
| smb_id | string | yes | – |
No output schema declared.
No examples provided.
import_booking_url ~296
Turn a public booking URL into a callable smb_id for send_message and capture_lead. But schedule_appointment only completes on Cal.com bound to our one connected account — the other 11 always fail schedule_appointment honestly, uncharged. Detects 12 platforms (Cal.com, Calendly, Doctolib, Booksy, Fresha, OpenTable, Setmore, Square, Acuity, Schedulista, Squarespace, BookMyCity). Idempotent — calling twice returns the same smb_id. [free, requires key] [limited]
| Name | Type | Req | Description |
|---|---|---|---|
| booking_url | string | yes | Full URL the user supplied. Must point at one of the 12 supported booking… |
| business_name | string | – | If omitted, auto-extracted from the page's <title> or og:title. |
| capabilities | array | – | Free-form capability tags (e.g., ['haircut','color','blowdry']). |
| contact_email | string | – | – |
| contact_phone | string | – | If omitted, the platform integration handles outreach. |
| country_code | string | – | ISO 3166-1 alpha-2 (e.g. 'US', 'FR'); routes compliance on later sends. |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| vertical | string | – | If omitted, inferred from the booking platform. |
No output schema declared.
No examples provided.
lookup_us_contracts ~133
Search US federal contract awards by company (recipient) name using the free USASpending.gov public API. Returns the top awards sorted by dollar amount: award ID, recipient name, award amount USD, awarding agency, NAICS code/description, and period of performance. Zero upstream cost, no key required. Data covers 2020-2026 procurement contracts. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| company_name | string | yes | Company or recipient name to search for in US federal contract awards (e.g.… |
| max_results | integer | – | Maximum number of contract awards to return (sorted by award amount… |
No output schema declared.
No examples provided.
map_trade_restriction ~235
Free cross-border screening of destination and parties: DOES NOT CLASSIFY THE PRODUCT: echoed back, never checked against export-control lists, so a controlled item to an unrestricted destination returns 'partial', never 'clear'. Not an export-control clearance -- classify HS/ECCN yourself. Never fabricates a tariff rate, a clear, or a restricted status. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| destination_country | string | yes | ISO 3166-1 alpha-2 code for the importing country (e.g. 'IR', 'CA', 'DE').… |
| hs_code | string | – | Optional Harmonized System code (e.g. '8471.30' for laptops). If provided,… |
| origin_country | string | – | Optional ISO 3166-1 alpha-2 code for the exporting country (e.g. 'US', 'DE').… |
| parties | array | – | Optional list of party names to screen (exporter, importer, freight forwarder,… |
| product | string | yes | Product name or description, e.g. 'laptop computers', 'crude oil', 'medical… |
No output schema declared.
No examples provided.
mint_key ~174
Mint a free-tier API key without email by signing agent_id + timestamp + nonce with the MACHINE_MINT_SECRET (HMAC-SHA256). Refused without that secret (invalid_request); not_configured if the operator has none set. No secret: use POST /keys/request. [free, no key] [limited]
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | A stable unique identifier for this agent (e.g. a UUID). The issued key is… |
| nonce | string | yes | Random value (UUID or hex). Prevents replay attacks — use a fresh nonce each… |
| signature | string | yes | HMAC-SHA256(agent_id + str(timestamp) + nonce, MACHINE_MINT_SECRET) as… |
| timestamp | integer | yes | Unix epoch seconds at signing time. Must be within 60s of server time. |
No output schema declared.
No examples provided.
preview_cost ~95
Return an expected cost estimate, latency estimate, and success-probability estimate for a proposed call before execution. Returns the exact price when it is fixed, and a min/max range when the cost depends on channel or outcome. It does not promise an accuracy percentage - check cost_range. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| operation | string | yes | – |
| params | object | yes | The same request body you would pass to the operation |
No output schema declared.
No examples provided.
schedule_appointment ~199
Check availability, book, or cancel via Cal.com. Only completes when the SMB's imported booking link is bound to this deployment's ONE connected Cal.com account; otherwise fails honestly (booking_destination_unmapped) with no charge. No working booking path exists yet for non-Cal.com platforms (voice AI, web form) — those SMBs fail honestly instead of a fabricated confirmation. [from $0.15/call, variable, not charged while no payment rail is on] [async→get_outcome] [limited]
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| customer | object | – | – |
| existing_appointment_id | string | – | Required for cancel |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| notes | string | – | – |
| requested_time | object | – | – |
| service | string | – | – |
| smb_id | string | yes | – |
No output schema declared.
No examples provided.
screen_sanctions ~184
Free screening of a name/entity (Latin or Arabic script) against sanctions lists: OFAC SDN (US Treasury), EU consolidated list (European Commission), UK Sanctions List (FCDO). THE UN CONSOLIDATED LIST IS NOT SCREENED -- no licence permits redistribution. Never fabricates a match or clear: check lists_screened; reason_code 'partial_screening' (never 'clear') if any source failed. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Optional ISO 3166-1 alpha-2 country code or country name (e.g. 'IR', 'Iran').… |
| name | string | yes | Name of the person or entity to screen, in Latin or Arabic script, e.g. 'Kim… |
| type | string | – | Optional entity type hint. 'person' for individuals, 'entity' for… |
No output schema declared.
No examples provided.
self_test ~54
Service health probe: runs 6 internal checks and reports how many passed. Confirms the server is up and responding - it does NOT probe each tool individually. Use to verify connectivity before production use. [free, no key]
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
send_message ~276
Send a message on behalf of an agent's user or an SMB across WhatsApp (free during launch), SMS, email, or voice, sent immediately, no scheduling. Every send passes a non-bypassable gate: TCPA, GDPR, CASL where modeled, else the service's own opt-in default (the Gulf included). Marketing on SMS, voice, WhatsApp and non-US email without recorded opt-in is rejected (compliance_violation receipt). US marketing email follows CAN-SPAM opt-out rules. [from $0.02/call, variable, not charged while no payment rail is on] [async→get_outcome] [Not available on this deployment: SMS, Voice.]
| Name | Type | Req | Description |
|---|---|---|---|
| business_id | string | – | Stable id for the recipient business; used for global demand shaping. |
| content | object | yes | – |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| message_type | string | yes | 'marketing' needs recorded opt-in, except US email (CAN-SPAM opt-out rules).… |
| on_behalf_of | string | – | Who this message is FOR (your end-user's name/label). On WhatsApp this opens a… |
| preferred_channel | string | – | – |
| recipient | object | yes | – |
No output schema declared.
No examples provided.
send_transactional_confirmation ~161
Idempotent transactional messages: OTPs, booking confirmations, payment receipts, cancellation notices. Falls back across configured channels; an unconfigured channel fails honestly rather than reporting a delivery that did not happen. [$0.02/per_call, not charged while no payment rail is on] [async→get_outcome] [Not available on this deployment: SMS.]
| Name | Type | Req | Description |
|---|---|---|---|
| confirmation_type | string | yes | – |
| data | object | yes | Type-specific payload; e.g., {otp_code} for otp, {appointment_time, smb_name}… |
| idempotency_key | string | – | Retry key: a 24h replay returns the original receipt, not re-run or charged. |
| preferred_channel | string | – | – |
| recipient | object | yes | – |
No output schema declared.
No examples provided.
verify_business ~78
Look up what we know about a business in our supply network: contact channels, capabilities, last verification. A DIRECTORY LOOKUP - it does not contact the business. Supply-network ids only, not osm:... ids. [free, no key] [limited]
| Name | Type | Req | Description |
|---|---|---|---|
| capability_to_verify | string | – | – |
| smb_id | string | yes | – |
No output schema declared.
No examples provided.
verify_company_record ~182
Free, live lookup of a company official registry record. Queries the GLEIF global LEI registry (primary, 2.6 million legal entities worldwide) and SEC EDGAR (US public companies) to return the official legal name, LEI, entity status, jurisdiction, registered address, and registry authority. Never fabricates: if the company is not found in these free registries, returns an honest not_found with the sources that were queried. [free, no key]
| Name | Type | Req | Description |
|---|---|---|---|
| country | string | – | Optional ISO 3166-1 alpha-2 country filter (e.g. US, DE, GB). Narrows GLEIF… |
| lei | string | – | Optional 20-character Legal Entity Identifier for a direct, precise lookup. |
| name | string | yes | Legal company name to look up, e.g. Apple Inc or Volkswagen AG. |
No output schema declared.
No examples provided.
What is the Agent Broker MCP server?
Agent Broker is an MCP server listed in the public MCP registry as dev.hatchloop/agent-broker. 23 MCP tools: compliance, verification, messaging, booking, US contracts. 15 need no key. This page covers its hosted endpoint (https://hatchloop.dev/mcp/agent-broker).
Is the Agent Broker MCP server safe to use?
Agent Broker scores 78 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 Agent Broker MCP server expose?
Agent Broker exposes 23 tools: find_business, verify_business, send_message, capture_lead, schedule_appointment, and 18 more. Their descriptions and schemas cost roughly 3,738 tokens of context every time the server is loaded.
Does the Agent Broker MCP server require authentication?
No. We connected to Agent Broker without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agent Broker MCP server still maintained?
Agent Broker is still listed as active in the MCP registry. We last reached this channel on 15 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.