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.

Surgemesh

REMOTE · API.SURGEMESH.COM

Agent-first social publishing. Preview: quotes and sandbox posts now; live posts and payments soon.

+2 this week 65 Trust /100

Last scanned (3 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Marketing and SEO

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 Security66
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • Authorisation not fully verified: no authorisation is required to call this server, and 28 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2364 tokens (~84/item across 28 items; 28 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 26% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_feedback" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 3 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “notify_me” functional
  • 2 Nov 26 −1
    • The server rewrote its instructions, which are the text every model session reads security
    • Destructive annotations: pass → 0 functional
    • New tool “send_feedback” functional
  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 29 Oct 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 28 Oct 26 62

    First indexed and scored.

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 5 Nov 2026 · Probed https://api.surgemesh.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=surgemesh.com CN=WE1,O=Google Trust Services,C=US 27 Oct 2026 25 Jan 2027 ECDSA 256 ECDSA-SHA256 2f03a4218b2ac6db0e7bda9c4bf3c0a0
SANs: surgemesh.com, api.surgemesh.com, *.api.surgemesh.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of api.surgemesh.com. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
surgemesh.com. present 2371 13 Verified
api.surgemesh.com. Verified address RRset verified with the apex keys
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
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'none'; frame-ancestors 'none'; base-uri 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=(), payment=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.surgemesh.com/mcp Verified 200
http (plaintext) http://api.surgemesh.com/mcp HTTPS enforced 301 https://api.surgemesh.com/mcp
MCP tools · 28 exposed · ~2,136 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
add_channel ~228

Add a channel directly (admin key). network "sandbox": a built-in test channel, no credentials, never publishes; it enforces the real limits of the network in simulates (bluesky, facebook or instagram; default bluesky). network "bluesky": credentials {handle, app_password} (identifier is accepted for handle) (an app password, never the account password). network "facebook": {token, page_id}; "instagram": {token, ig_user_id}. Credentials are checked with the network before anything is stored (invalid = 400 credentials_invalid, nothing saved), encrypted at rest, and never returned or echoed. No credentials to hand? Use connect_channel (the owner taps a link) or a sandbox test channel.

NameTypeReqDescription
brand_idstringyes–
credentialsobject–Not for sandbox. bluesky: handle (or identifier) + app_password; facebook: token + page_id; instagram: token + ig_user_id
labelstring––
networkstringyes–
simulatesstring–sandbox only

No output schema declared.

No examples provided.

cancel_post ~29

Cancel a queued post. Undelivered deliveries are refunded to credit.

NameTypeReqDescription
idstringyes–

No output schema declared.

No examples provided.

check_dns_verification ~33

Check whether the TXT record is visible; verifies the account when it is.

NameTypeReqDescription
verification_idstringyes–

No output schema declared.

No examples provided.

confirm_email_verification ~36

Submit the 6-digit code from the verification email.

NameTypeReqDescription
codestringyes–
verification_idstringyes–

No output schema declared.

No examples provided.

connect_channel ~102

Start a one-tap connect for a brand on an OAuth or app-password network (networks marked coming soon in list_networks are refused). Returns connect_url: give it to the account owner to open once. Then poll get_connect_status.

NameTypeReqDescription
brand_idstringyes–
labelstring––
networkstringyes–
optionsobject–Network options listed by list_networks (e.g. board_id, organization_id)

No output schema declared.

No examples provided.

create_checkout_link ~115

Card checkout for a human (coming soon): returns a Stripe-hosted checkout_url for a credit pack (pack_5 $5, pack_20 $20, pack_100 $100; each pack buys exactly its price in credit). Give the link to the person paying; credits arrive only after Stripe confirms. Verified owners, admin key. 503 checkout_not_enabled until switched on.

NameTypeReqDescription
idempotency_keystring–Optional. Reuse on retries so the action happens once.
packstringyes–

No output schema declared.

No examples provided.

create_post ~121

Schedule a post to one or more channels. idempotency_key is required; retries with the same key never double-post or double-charge. Optional max_price_usd refuses a price above your cap. Preview: posts are validated and priced in the sandbox, not published yet.

NameTypeReqDescription
bodystringyes–
brand_idstringyes–
channelsarrayyes–
idempotency_keystringyes–
max_price_usdnumber––
media_urlsarray––
scheduled_atstringyes–

No output schema declared.

No examples provided.

disconnect_channel ~37

Disconnect a channel: erases its stored credentials and revokes the provider token where the network supports it.

NameTypeReqDescription
channel_idstringyes–

No output schema declared.

No examples provided.

get_analytics ~59

Posts, deliveries, published, failed and spend over time (UTC), with a per-brand breakdown.

NameTypeReqDescription
brand_idstring––
fromstring––
granularitystring––
tostring––

No output schema declared.

No examples provided.

get_connect_status ~35

Status of a connect session: pending, connected (with channel_id), failed or expired.

NameTypeReqDescription
connect_idstringyes–

No output schema declared.

No examples provided.

get_onboarding ~29

Onboarding status: verification state, remaining steps and the exact next call. Start here after signup.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_pricing ~56

Surgemesh prices: base per delivery, a hard ceiling (never more than $0.06 per delivery), time-of-day pricing (quieter times cost less, busier times cost more), credit packs. No auth needed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_quote ~156

Exact price quote (locks at post acceptance; guard with max_price_usd) for N deliveries at scheduled_at (ISO 8601 UTC, e.g. 2026-10-29T15:00:00Z), or for a network mix (networks, e.g. {"bluesky": 1, "facebook": 2}; adds by_network), with cheaper_times (nearby times and their exact prices) when a nearby time costs less. No auth needed.

NameTypeReqDescription
deliveriesinteger––
networks––Optional network mix: an object {network: deliveries} or the REST string "bluesky:1,facebook:2". Overrides deliveries.
scheduled_atstringyes–

No output schema declared.

No examples provided.

get_referral_code ~58

Your referral code, share link and stats (referred signups, qualified, credits earned and pending). Referral rewards are Surgemesh credits only, never cash, and are coming soon; codes can be shared now. Verified owners only.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_topup_link ~140

Coming soon (payments are not enabled yet). Payment link to buy a credit pack (pack_5 $5, pack_20 $20, pack_100 $100; each pack buys exactly its price in credit). Rails: mpp_card (card via Stripe Shared Payment Token), mpp_stablecoin (USDC.e on Tempo, USDC on Solana), x402 (USDC on Base); each shows live or coming_soon. POST to paymentLink with your Bearer key, pay the 402 challenge, retry. No payment happens in this tool.

NameTypeReqDescription
packstringyes–
railstring––

No output schema declared.

No examples provided.

get_usage ~39

Account: plan, verification, credit, sandbox allowance (monthly_allowance, posts_used_this_month, posts_remaining_this_month, resets_at) and settings.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_verification ~32

Status of one verification (pending, verified, expired, failed, denied).

NameTypeReqDescription
verification_idstringyes–

No output schema declared.

No examples provided.

list_brands ~14

Brands in this account.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_channels ~44

Channels this key can post to (connected social accounts and sandbox test channels). Disconnected channels are hidden unless include_disconnected is true.

NameTypeReqDescription
include_disconnectedboolean––

No output schema declared.

No examples provided.

list_networks ~64

Every supported network: status (available, connect_pending_review, connect_pending_setup = coming soon), how to connect it, and the limits enforced on every post (text, hashtags, media count, types, sizes), plus the built-in sandbox test channel. No auth needed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_posts ~51

Recent posts for a brand: status (pending, accepted, rejected, cancelled), cancelled, sandbox, price_usd (quoted), charged_usd, per-channel delivery state.

NameTypeReqDescription
brand_idstringyes–

No output schema declared.

No examples provided.

notify_me ~158

Payments are not open yet. Ask for one email when they open (topic "payments_open"). With a key, the account owner's email is used; without a key, send email and accept_terms: true. Re-asking is safe (already: true, no duplicate). Optional intended_pack says which pack you plan to buy. One email, then the address is deleted 30 days later; the email has a one-click unsubscribe.

NameTypeReqDescription
accept_termsboolean–Only without a key: accepts https://surgemesh.com/terms and https://surgemesh.com/privacy
emailstring–Only without a key: the address to notify
intended_packstring––
topicstringyes–

No output schema declared.

No examples provided.

request_owner_approval ~73

Email the account owner a one-tap Approve link (24 h, single use). Poll get_verification until verified or denied.

NameTypeReqDescription
callback_urlstring––
idempotency_keystring–Optional. Reuse on retries so the action happens once.
notestring––

No output schema declared.

No examples provided.

rotate_my_key ~76

Rotate the calling key: returns a new key (shown once) with the same scopes; the old key keeps working for grace_seconds (default 3600, 0 = revoke now).

NameTypeReqDescription
grace_secondsinteger––
idempotency_keystring–Optional. Reuse on retries so the action happens once.

No output schema declared.

No examples provided.

send_feedback ~165

Tell Surgemesh what broke, confused you or is missing (no key needed; with a key the note is linked to your account). Include error_code and request_id from the response you got, and the tool or path as topic. The Surgemesh team reads every note; there is no reply. Never include secrets, keys or personal data.

NameTypeReqDescription
error_codestring–The "error" field you got back, e.g. invalid_field
kindstringyes–
messagestringyes–
request_idstring–The x-request-id header of the response, if you have it
topicstring–A tool name (e.g. create_post) or API path (e.g. /v1/quote)

No output schema declared.

No examples provided.

start_dns_verification ~62

Get a TXT record to publish on the account email domain (or a parent domain). Then call check_dns_verification.

NameTypeReqDescription
domainstringyes–
idempotency_keystring–Optional. Reuse on retries so the action happens once.

No output schema declared.

No examples provided.

start_email_verification ~62

Email a 6-digit code to the account email (expires in 10 minutes, 5 attempts). Then call confirm_email_verification with the code.

NameTypeReqDescription
idempotency_keystring–Optional. Reuse on retries so the action happens once.

No output schema declared.

No examples provided.

update_account_settings ~62

Account settings (admin key). trend_opt_out: true opts this account out of contributing to any aggregated trend statistics Surgemesh may create in future (see Terms); none exist today. get_usage shows the current setting.

NameTypeReqDescription
trend_opt_outbooleanyes–

No output schema declared.

No examples provided.

Install

How do I install the Surgemesh MCP server?

Surgemesh is a hosted endpoint at https://api.surgemesh.com/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.surgemesh.com

# add to Claude Code
claude mcp add --transport http com-surgemesh-surgemesh 'https://api.surgemesh.com/mcp'
Common questions

What is the Surgemesh MCP server?

Surgemesh is an MCP server listed in the public MCP registry as com.surgemesh/surgemesh. Agent-first social publishing. Preview: quotes and sandbox posts now; live posts and payments soon. This page covers its hosted endpoint (https://api.surgemesh.com/mcp).

Is the Surgemesh MCP server safe to use?

Surgemesh scores 65 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 Surgemesh MCP server expose?

Surgemesh exposes 28 tools: get_pricing, get_quote, list_channels, add_channel, list_brands, and 23 more. Their descriptions and schemas cost roughly 2,136 tokens of context every time the server is loaded.

Does the Surgemesh MCP server require authentication?

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

Is the Surgemesh MCP server still maintained?

Surgemesh is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.