Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Mekler AI

REMOTE · API.MEKLER.AI

Research, inference, data/web/email tools, and x402 conformance, service catalog and grade feeds.

Available components

−1 this week 73 Trust /100

Last scanned (15 hours ago)

Scores higher than 59% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Trust breakdown (7 categories)

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
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3432 tokens (~107/item across 32 items; 32 tools + 0 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 Management93
  • Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 3 breaking changes, 0 auth/transport breaks, 8 additions. See how to fix → Fail
Tool Coverage68
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 5% 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
  • We read all 32 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 18 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 18 Nov 26 −1
    • Stability: pass → fail ▼ security
    • Tool “retrieve_listing” rewrote its description, which is the text the model reads security
    • Tool “search_listings” rewrote its description, which is the text the model reads security
    • Schema quality: pass → fail ▼ functional
    • “retrieve_listing” added an optional parameter “history_cursor” cosmetic
    • “search_listings” added an optional parameter “payment_check” cosmetic
  • 17 Nov 26 0
    • Tool “summarize_directory_status” rewrote its description, which is the text the model reads security
    • “summarize_directory_status” added an optional parameter “matrix_cursor” cosmetic
    • “summarize_directory_status” added an optional parameter “matrix_limit” cosmetic
  • 16 Nov 26 0
    • Tool “request_listing_update” rewrote its description, which is the text the model reads security
    • Tool “search_listings” rewrote its description, which is the text the model reads security
    • “request_listing_update” added an optional parameter “acknowledge_hidden” cosmetic
    • “search_listings” added an optional parameter “page” cosmetic
  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 7 Nov 26 0
    • A breaking change shipped without a version bump: still 0.1.1 ▼ security
    • “retrieve_listing” changed the type of “listing_id”: string|null → string ▼ functional
    • “retrieve_listing” reworded the description of “listing_id” cosmetic
  • 6 Nov 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
  • 4 Nov 26 0
    • Stability: 0.97 → pass security
Diagnostics

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 21 Nov 2026 · Probed https://api.mekler.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.mekler.ai CN=Amazon RSA 2048 M01,O=Amazon,C=US 3 Oct 2026 18 Apr 2027 RSA 2048 SHA256-RSA 5b5183a33278109795f1518a79dd751
SANs: api.mekler.ai
CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 77312380b9d6688a33b1ed9bf9ccda68e0e0f
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.mekler.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
mekler.ai. No DS 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
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.mekler.ai/mcp Verified 200
http (plaintext) http://api.mekler.ai/mcp HTTPS enforced
MCP tools · 32 exposed · ~3,432 tokens

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 →

Tool Tokens
confirm_ownership_proof ~147

Confirm a one-hour domain challenge with the same private requester key. Exact HTTPS origin and path must match. Returns a 90 day listing-control credential; identical retries recover that grant. A new proof revokes prior credentials. Confirmation does not approve branding or change grades. For a pending private contact, retry the original challenge_id/requester_key with contact_code. For a correction, use update_id and its private requester_key; an exact update-bound domain file queues review without publishing the proposed fields. Never signs payments.

NameTypeReqDescription
challenge_idstring|null––
contact_codestring––
requester_keystring|null––
update_idstring––

No output schema declared.

No examples provided.

export_listings ~115

Export up to 10000 visible x402 directory services with attributed source facts, measured health and grade history, first seen, scan counts, provenance and explicit truncation. Returns gzip+base64 JSON and a digest; large results use a 60 second signed download URL. Costs 0.25 USDC on Base or Solana. Reuse the original body and payment proof for exact 30 day result recovery. Never signs payments.

NameTypeReqDescription
idempotency_keystringyes–
payment_signaturestring––

No output schema declared.

No examples provided.

get_scan_report ~41

Read a completed public cached report by report_id. Reports expire after 24 hours; this tool never purchases a replacement.

NameTypeReqDescription
report_idstringyes–

No output schema declared.

No examples provided.

get_scan_status ~49

Read a conformance job state with job_id and recovery_capability. Polling never starts work or settles payment.

NameTypeReqDescription
job_idstringyes–
recovery_capabilitystringyes–

No output schema declared.

No examples provided.

get_service ~43

Get a complete public service or operation contract by slug, operation ID, name, or endpoint URL.

NameTypeReqDescription
idstringyes–
referral_codestring––

No output schema declared.

No examples provided.

get_trial_access ~40

Get the service request and standard wallet-auth instructions. First signed execution enrolls automatically; no wallet funds or payment required.

NameTypeReqDescription
operationstringyes–

No output schema declared.

No examples provided.

get_trial_offer ~25

Read the adjustable free-use offer, wallet authentication, allowance and explicit paid transition.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_categories ~22

Read categories present in visible identity-reviewed directory listings. Never signs payments.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_conformance_checks ~35

Read the versioned 25-check linter and separate 14-check compliance catalogs, grading rules and unknown-evidence semantics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_grade_changes ~128

Read ordered new, grade_changed and rescanned events with previous grades and scores. Default 200, maximum 1000; signed watermark cursors. History retains 30 days or 50000 events; expired cursors return 410. Costs 0.01 USDC per page on Base or Solana. Use a fresh idempotency key per page; retain the original body and proof for exact recovery. Never signs payments.

NameTypeReqDescription
cursorstring––
idempotency_keystringyes–
limitinteger––
payment_signaturestring––

No output schema declared.

No examples provided.

list_networks ~33

Read canonical network identifiers in visible directory routes. Imported network claims are attributed and unverified until observed. Never signs payments.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_offer_changes ~78

Read changes observed in unsigned payment challenges. Before/after fingerprints preserve payout privacy. A drained cursor advances to new observations on later polls; retain it. No paid delivery is inferred. Never signs payments.

NameTypeReqDescription
cursorstring––
limitinteger––
listing_idstring––
sinceinteger––

No output schema declared.

No examples provided.

referral_accept_terms ~84

Accept a newer version of the referral terms to keep earning. arguments: terms_version and terms_digest from referral_program. Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_acknowledge ~88

Mark notices already served by referral_notices as read up to a cursor. arguments: cursor (integer) and optional private_cursor. Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_notices ~89

Read published program notices and the referrer's private account events. arguments: optional cursor, limit (1-50) and private_cursor. Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_program ~20

Read current Mekler referral availability, terms and commission offer.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

referral_receipts ~88

Page through a referrer's commission receipts, oldest first. arguments: optional cursor (last seen) and limit (1-50). Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_register ~93

Register a wallet as a Mekler referrer and receive a referral code. arguments: terms_version and terms_digest from referral_program, which explicitly accept those exact terms. Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_rotate ~95

Move a referral registration to a new wallet without losing history. arguments: old_wallet and new_wallet; then send proof (old wallet) and new_proof (new wallet). Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

referral_status ~85

Read a registered referrer's code, referral link, accepted versus current terms and whether action is required. arguments: none. Call without proof to get a SIWx challenge, sign it with the referrer wallet, then call again with proof. No payment is authorized.

NameTypeReqDescription
argumentsobject––
new_proofobject––
proofobject––

No output schema declared.

No examples provided.

reissue_owner_token ~135

Request one email-based ownership-credential replacement for an existing verified private contact. POST origin for a uniform 202 response whether eligible or not. POST the same origin and recovery_code to confirm within 15 minutes. Domain control and original ownership scope are checked; success replaces the prior credential without extending the original 90 day expiry. The code is single-use with idempotent recovery of the same replacement. Revoked/expired grants or changed domains need a fresh ownership proof. Never put a recovery code or control credential in a URL. Never signs payments.

NameTypeReqDescription
originstringyes–
recovery_codestring––

No output schema declared.

No examples provided.

request_listing_update ~294

Request a free reviewed listing correction with X-Mekler-Listing-Control, current revision, a fresh private requester_key and exact changes. Reuse that same requester_key and identical body after an uncertain response; it pins one request, and changed input conflicts. A recovery email is optional; without a verified email, return to the authenticated page to check the outcome. Name/description/category, a same-origin website URL and the full replacement active endpoint list (up to 50 GET/POST paths) are supported. Publish the returned change-bound HTTPS verification file and confirm update_id within 72 hours through confirm-ownership-proof. Confirmation queues review; it never publishes raw submitted text. We review corrections within 2 days, normally on an hourly scheduled review. Every field receives an outcome with fixed reasons. A newer confirmed request supersedes an earlier pending request. Missed deadlines are incidents with visible outcomes and alerts. Removed-route history is retained. action status with listing_id or origin reads private controls; optional request_id reads that correction outcome. Private data never enters public directory projections. Never signs payments.

NameTypeReqDescription
acknowledge_hiddenboolean––
action–––
changesobject––
control_credentialstringyes–
listing_idstring––
originstring––
request_idstring––
requester_keystring––
revisioninteger––

No output schema declared.

No examples provided.

retrieve_health_checks ~87

Page through fixed safe monitoring observations for one listing or the whole visible catalog. Current hiding and attribution controls apply to retained history. No captured target body, contact or payout address is returned. Never signs payments.

NameTypeReqDescription
cursorstring––
limitinteger––
listing_idstring––
route_idstring––
sinceinteger––

No output schema declared.

No examples provided.

retrieve_listing ~318

Read one currently visible listing and its dated evidence. Optional assessment_history contains ten actual completed and applied Directory observations or retained linter scans, with source and actual rules version (unknown if absent). Completed and applied unassessed attempts have null grade/score and a fixed reason; they are never F or the shown grade. Profile HTML groups consecutive same-reason unassessed attempts while API rows retain every attempt. Up to 52 Directory observations and 100 linter scans are retained. Supply the returned history_cursor for ten more raw history rows; continuation returns listing_id and assessment_history only. Cursors expire after one hour or a history change; current identity, hiding, canonical, grade and health masks are rechecked on every page. Hidden or ineligible listings return 404; stale history cursors return 410; invalid artifacts fail 503. No job discovery, new probes, grade change or paid delivery certification. Public directory reads share 30 requests per client IP per UTC minute. Search returns at most 100 services per call; a 963-service snapshot needs 10 calls at limit=100. Follow returned cursors and avoid concurrent bursts; 429 means wait for the next UTC minute. No quota increase is implied. Never signs payments.

NameTypeReqDescription
history_cursorstring–Opaque returned assessment_history.next_cursor. Never fabricate or alter it.
listing_idstringyesVisible listing identity, its unique 16-character public reference, or exact service host including an optional port. Hidden, unknown and ambiguous references return 404.

No output schema declared.

No examples provided.

retrieve_listing_history ~117

Page through Mekler uptime, latency or observed price history for one listing. Raw history retains 30 days; UTC daily aggregates are retained indefinitely. Unknown input/auth/rate-limit observations are excluded from uptime denominators. This is configuration/reachability evidence, not paid-delivery proof. Never signs payments.

NameTypeReqDescription
cursorstring––
interval–––
limitinteger––
listing_idstringyes–
route_idstring––
series–––
sinceinteger––

No output schema declared.

No examples provided.

rotate_trial ~90

Write: request a wallet-rotation challenge with old_wallet/new_wallet/request_id; then submit old_proof/new_proof signed with both keys. Usage is preserved.

NameTypeReqDescription
networkstring––
new_proofobject––
new_walletstring––
old_proofobject––
old_walletstring––
request_idstring––

No output schema declared.

No examples provided.

scan_origin ~204

Start or recover an asynchronous x402 conformance scan. For new origin-only calls, this MCP tool defaults to quote_mode fast and returns an unsigned 402 quote without starting a scan. Capability-only recovery requires the original input or proof; use get_scan_status for capability polling. Resend the same arguments with payment_signature only after independent payment authorization. Supplying idempotency_key without quote_mode retains compute-first admission. Save the job/capability and poll. Never signs payments.

NameTypeReqDescription
idempotency_keystring–Required for compute-first mode. Omit both this and quote_mode for the MCP tool's unsigned fast quote. Retain any supplied key for retries.
originstringyesPublic HTTP(S) origin only; no credentials, path, query or fragment. Use paths for same-origin paths.
pathsarray––
payment_signaturestring––
quote_modestring––
recovery_capabilitystring––

No output schema declared.

No examples provided.

search_listings ~369

Find x402 services imported from attributed catalogs or scanned by Mekler. Filter by task text, host, category, network, source, tier, grade or owner control. Only identity-reviewed listings with a grade and a current known health reading are displayed. Ineligible listings are retained privately until evidence qualifies them; unknown prices stay unknown. Payment-ready means a recent valid unsigned challenge; it does not certify useful paid delivery. Numbered page requests read the current eligible results and count from one snapshot; out-of-range pages clamp to the last page. A page cannot be combined with a cursor. Immutable cursors retain ordering while current privacy controls still apply. Optional payment_check=passed requires all three explicit passes under the selected exact rules version and excludes blocked/unknown evidence. visible_categories supplies the publication-derived global menu before user filters. Public directory reads share 30 requests per client IP per UTC minute. Search returns at most 100 services per call; a 963-service snapshot needs 10 calls at limit=100. Follow returned cursors and avoid concurrent bursts; 429 means wait for the next UTC minute. No quota increase is implied. Never signs payments.

NameTypeReqDescription
categorystring––
cursorstring––
featuredboolean––
gradestring––
hoststring––
include_delistedboolean––
limitinteger––
networkstring––
owner_verifiedboolean––
pageinteger–One-based page over current eligible results. Clamped to the last page; cannot be combined with cursor.
payment_checkstring––
sortstring––
sourcestring––
textstring––
tierstring––

No output schema declared.

No examples provided.

search_services ~38

Find Mekler paid operations for a task, including exclusions and useful combinations.

NameTypeReqDescription
querystringyes–
referral_codestring––

No output schema declared.

No examples provided.

start_ownership_proof ~149

Start a one-hour domain challenge bound to your private random 32-byte requester key in lowercase hex. Publish the returned JSON exactly at its HTTPS well-known URL. Keep the requester key private. An imported directory listing or completed scan is required before confirmation. No payment or target credentials are sent. Optionally supply contact_email and email_consent true for transactional verification/recovery/outcome messages. Contact stays private and must be verified by a mailed code after domain confirmation. No message is sent before successful domain proof. Never signs payments.

NameTypeReqDescription
contact_emailstring––
email_consentboolean––
originstringyes–
requester_keystring|nullyes–

No output schema declared.

No examples provided.

summarize_directory_status ~100

Read catalog-wide measured state counts and the latest completed monitoring cycle. Set matrix_limit=0 for aggregate headlines only, or 1–100 for bounded service/history rows and signed current-privacy cursors. Omit matrix_limit for the compatible complete matrix. Counts always cover the entire visible catalog. Missing checks remain unknown; this does not certify paid delivery. Never signs payments.

NameTypeReqDescription
matrix_cursorstring––
matrix_limitinteger––

No output schema declared.

No examples provided.

update_listing_preferences ~133

Use X-Mekler-Listing-Control and the expected revision to hide a listing, suppress branding or revoke access. Domain proof is rechecked after seven days; failed, stale, revoked or expired credentials deny control. Concurrent writes return 409. Suppression affects current reads, new exports/feed pages and old search cursors; previously purchased snapshots remain recoverable. Never signs payments.

NameTypeReqDescription
control_credentialstringyes–
hiddenboolean––
listing_idstring|nullyes–
revisionintegeryes–
revokeboolean––
suppress_brandingboolean––

No output schema declared.

No examples provided.

Install

How do I install the Mekler AI MCP server?

Mekler AI is a hosted endpoint at https://api.mekler.ai/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.

remote · api.mekler.ai

# add to Claude Code
claude mcp add --transport http ai-mekler-agent-discovery 'https://api.mekler.ai/mcp'
Common questions

What is the Mekler AI MCP server?

Mekler AI is an MCP server listed in the public MCP registry as ai.mekler/agent-discovery. Research, inference, data/web/email tools, and x402 conformance, service catalog and grade feeds. This page covers its hosted endpoint (https://api.mekler.ai/mcp).

Is the Mekler AI MCP server safe to use?

Mekler AI 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 Mekler AI MCP server expose?

Mekler AI exposes 32 tools: search_services, get_service, scan_origin, get_scan_status, get_scan_report, and 27 more. Their descriptions and schemas cost roughly 3,432 tokens of context every time the server is loaded.

Does the Mekler AI MCP server require authentication?

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

Is the Mekler AI MCP server still maintained?

Mekler AI 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 Mekler AI MCP server?

VerifyMCP ran 12 checks on Mekler AI, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Mekler AI: Authorization. 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.