Social Perks
REMOTE · SOCIALPERKS.APP · SCANNED SEP 20
Agent-native marketing platform: create campaigns, submit proofs, review submissions.
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 Security63
- 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 10 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 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 Usability76
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 836 tokens (~83/item across 10 items; 10 tools + 0 resources), lean.Pass
- 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 Coverage87
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 62% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
- Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
How do I install the Social Perks MCP server?
Social Perks is a hosted endpoint at https://socialperks.app/api/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 · socialperks.app
claude mcp add --transport http benzatkulak-collab-socialperks 'https://socialperks.app/api/mcp'
{
"mcpServers": {
"benzatkulak-collab-socialperks": {
"url": "https://socialperks.app/api/mcp"
}
}
} {
"servers": {
"benzatkulak-collab-socialperks": {
"type": "http",
"url": "https://socialperks.app/api/mcp"
}
}
} [mcp_servers.benzatkulak-collab-socialperks] url = "https://socialperks.app/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"benzatkulak-collab-socialperks": {
"type": "remote",
"url": "https://socialperks.app/api/mcp",
"enabled": true
}
}
} openclaw mcp add benzatkulak-collab-socialperks --url 'https://socialperks.app/api/mcp' --transport streamable-http
mcp_servers:
benzatkulak-collab-socialperks:
url: "https://socialperks.app/api/mcp" {
"McpServers": {
"benzatkulak-collab-socialperks": {
"Transport": "http",
"Url": "https://socialperks.app/api/mcp"
}
}
} assistant mcp add benzatkulak-collab-socialperks -t streamable-http -u 'https://socialperks.app/api/mcp'
{
"mcpServers": {
"benzatkulak-collab-socialperks": {
"type": "http",
"url": "https://socialperks.app/api/mcp"
}
}
} 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.
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Aug 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
- 5 Aug 26 0
- TLS certificate: unverified → pass ▲ security
- 4 Aug 26 0
- TLS certificate: pass → unverified ▼ security
- Tool “getBenchmarks” rewrote its description, which is the text the model reads security
- Tool “listActions” rewrote its description, which is the text the model reads security
- “getBenchmarks” added an optional parameter “businessType” cosmetic
- “getBenchmarks” dropped the optional parameter “industry” cosmetic
- 31 Jul 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
- 27 Jul 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
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 20 Sept 2026 · Probed https://socialperks.app/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=socialperks.app | CN=YR2,O=Let's Encrypt,C=US | 29 Jul 2026 | 27 Oct 2026 | RSA 2048 | SHA256-RSA | 60f6adfb37354a1d6a97c1591aad69c6b16 |
| SANs: socialperks.app | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of socialperks.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| socialperks.app. | 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 |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' https://va.vercel-scripts.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; img-src 'self' data: blob: https:; font-src 'self' data: https://fonts.gstatic.com; connect-src 'self' https://api.stripe.com https://va.vercel-scripts.com https://vitals.vercel-insights.com https://va.vercel-scripts.com; frame-ancestors 'none'; base-uri 'self'; form-action 'self'; object-src 'none'; upgrade-insecure-requests; report-uri /api/v1/csp-report; report-to csp-endpoint |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://socialperks.app/api/mcp | Verified | 200 | |
| http (plaintext) | http://socialperks.app/api/mcp | HTTPS enforced | 308 | https://socialperks.app/api/mcp |
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 →
createCampaign ~197
Create and launch a new campaign for the calling business. Returns the campaign id, name, and dashboard URL. The campaign goes live immediately — no separate publish step.
| Name | Type | Req | Description |
|---|---|---|---|
| actions | array | yes | Action IDs the campaign accepts (e.g. ['ig_st'] for an Instagram Story Tag). |
| businessId | string | yes | The business owning this campaign. Must match the API key's business. |
| description | string | – | Optional internal description |
| discountType | string | yes | Discount denomination: 'pct' for percentage, 'dol' for dollars off. |
| discountValue | number | yes | Discount amount. Capped at 100 for pct, 10000 for dol. |
| expiresInDays | integer | – | Days until the campaign auto-expires. Default 60. |
| maxCompletions | integer|null | – | Optional cap on total completions. Null = no cap. |
| name | string | yes | Customer-facing campaign name |
No output schema declared.
No examples provided.
getBenchmarks ~57
Get industry benchmarks (engagement rate, conversion rate, etc.) for a business type.
| Name | Type | Req | Description |
|---|---|---|---|
| businessType | string | – | Industry name or slug (e.g. 'restaurants', 'coffee-shops'). Omit for the full catalog. |
No output schema declared.
No examples provided.
getCampaignStats ~59
Get summary stats for a single campaign — total submissions, approved count, conversion rate, perks issued, and time-to-first-submission. Useful for an agent reporting back to its user.
| Name | Type | Req | Description |
|---|---|---|---|
| campaignId | string | yes | Campaign to fetch stats for. |
No output schema declared.
No examples provided.
getPricing ~78
Get the market-rate pricing for a marketing action. Returns USD value and recommended perk type/value.
| Name | Type | Req | Description |
|---|---|---|---|
| actionId | string | – | Action ID (e.g. ig_post, google_review) |
| businessType | string | – | Business type modifier (default: general) |
| platformId | string | – | Platform ID (e.g. instagram, google) |
No output schema declared.
No examples provided.
listActions ~69
List the 125 marketing actions available on Social Perks. Filterable by platform, type, and effort.
| Name | Type | Req | Description |
|---|---|---|---|
| maxEffort | integer | – | – |
| page | integer | – | – |
| perPage | integer | – | – |
| platformId | string | – | – |
| type | string | – | – |
No output schema declared.
No examples provided.
listCampaigns ~28
List campaigns. Requires auth — returns the caller's campaigns.
| Name | Type | Req | Description |
|---|---|---|---|
| status | string | – | – |
No output schema declared.
No examples provided.
listSubmissions ~71
List submissions for a business or campaign, filterable by state (pending/approved/rejected). Returns paginated results.
| Name | Type | Req | Description |
|---|---|---|---|
| businessId | string | – | – |
| campaignId | string | – | – |
| page | integer | – | – |
| perPage | integer | – | – |
| state | string | – | – |
No output schema declared.
No examples provided.
reviewSubmission ~93
Approve or reject a submission. Approving releases the perk; rejecting requires a reason. Use this when the business chooses manual review over auto-verification.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | string | yes | Approve releases the perk. Reject explains why the proof was insufficient. |
| reason | string | – | Required when decision='reject'. 1-500 chars. |
| submissionId | string | yes | Submission id from a prior submitProof call. |
No output schema declared.
No examples provided.
searchInfluencers ~32
Search influencers by platform and follower count.
| Name | Type | Req | Description |
|---|---|---|---|
| minFollowers | integer | – | – |
| platform | string | – | – |
No output schema declared.
No examples provided.
submitProof ~152
Submit proof of completion for a campaign action — a public URL to a post, a screenshot, a video, or platform-verified data. The submission enters a review queue (or auto-approves depending on the campaign's verification mode).
| Name | Type | Req | Description |
|---|---|---|---|
| actionId | string | yes | Specific action being completed (must be allowed by the campaign). |
| campaignId | string | yes | Campaign the submission applies to. |
| metadata | object | – | Optional bag of context (poster handle, post timestamp, etc.). |
| proofType | string | yes | How the proof was captured. 'url' triggers automated verification. |
| proofUrl | string | yes | Public URL of the proof. For url-type submissions, the platform verifier will fetch this. |
No output schema declared.
No examples provided.
What is the Social Perks MCP server?
Social Perks is an MCP server listed in the public MCP registry as io.github.benzatkulak-collab/socialperks. Agent-native marketing platform: create campaigns, submit proofs, review submissions. This page covers its hosted endpoint (https://socialperks.app/api/mcp).
Is the Social Perks MCP server safe to use?
Social Perks scores 77 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 Social Perks MCP server expose?
Social Perks exposes 10 tools: getPricing, listActions, getBenchmarks, listCampaigns, searchInfluencers, and 5 more. Their descriptions and schemas cost roughly 836 tokens of context every time the server is loaded.
Does the Social Perks MCP server require authentication?
No. We connected to Social Perks without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Social Perks MCP server still maintained?
Social Perks is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.