ScriptMasterLabs — measured November 20, 2026. Primary sources: SOCi's November 19, 2026 PR Newswire launch release and SOCi's Genius MCP page (soci.ai/genius-mcp), both read first-hand November 20, 2026. Gate test: SML harness, local-heuristic-v1, calibrated=false.

The SOCi MCP server, generally available to all SOCi customers since SOCi's November 19, 2026 announcement, lets AI assistants and agent frameworks that support the Model Context Protocol call SOCi's standard platform tools, agentic tools, and reporting and insights directly, so the results become part of the context those assistants work from.

·

How does the SOCi MCP server work?

The SOCi MCP server, generally available to all SOCi customers since SOCi's November 19, 2026 announcement, lets AI assistants and agent frameworks that support the Model Context Protocol call SOCi's standard platform tools, agentic tools, and reporting and insights directly, so the results become part of the context those assistants work from — a marketer can ask an assistant to show SOCi locations or find locations that need review responses without opening another interface. SOCi's own Genius MCP page counts the surface plainly: 4 essential capabilities — 2 Ask (ask how-to questions about SOCi; analyze themes across reviews) and 2 Act (update listing fields such as hours, categories, attributes and images; publish posts to Facebook, Instagram, Google, LinkedIn and X) — behind a context layer fed by more than 140 integrations (Snowflake, Salesforce, Olo, Semrush and Canva among them, alongside premier connections to Google, Meta, Yelp, Apple and Bing) and guiding more than 400,000 deployed Genius Agents across three named agents: Reputation, Local Search and Social. Its controls, counted from the same two sources, are 3: permission inheritance (every action runs under the connecting user's permissions — if they cannot do it in SOCi, their assistant cannot either), flagged data-changing tools (flagged so the AI client can ask the user to confirm before it acts), and SOCi Shield approval paths for work that needs a person's judgment, under SOC 2 Type II and ISO/IEC 42001 credentials. Per-action decision scores named in either source: 0. A flag says an action changes data; it does not grade whether THIS publish, to THESE five networks, with THIS copy, should fire. That graded decision is what ScriptMasterLabs sells. ScriptMasterLabs Verdict Protocol costs $0.005 USDC per decision and $0.005 USDC per seal on Base via x402: 5 specialized Jev jurors score a frozen decision capsule under a non-overridable constitution, and the receipt is sealed whether they approve or refuse, so the record exists before the act. In ScriptMasterLabs' live gate test today, the gate never auto-acted a SOCi-shaped write in any form: publishing posts to five networks and updating listings without asking was held — the gate chose hold review at 0.9167 in bounded scope form and held at 0.50 advisory in bounded sentence form — while the read it was asked to protect, analyzing review themes, auto-acted at 0.9286 in sentence form. The full pattern is decision-gated machine payments: https://scriptmasterlabs.com/decision-gated-payments

Pricing at a glance

Proof: Verdict Protocol settlements (SELF-PROOF)

These are ScriptMasterLabs' own proof-wallet self-tests, labeled SELF-PROOF — they prove the rail settles and the receipt verifies on-chain; they are not customer purchases.

SettlementAmountDateOn-chain proof
Verdict decision receipt$0.25 USDC (price at the time of settlement; the live price verified November 20, 2026 is $0.005 USDC per decision)October 12, 2026Base tx 0xfa3ec31ff345167a474c682cec4e2eac505cfdd570e158961a233187be5f6f1c, block 52522538, status 0x1
Verdict seal receipt$0.01 USDC (price at the time of settlement; the live price verified November 20, 2026 is $0.005 USDC per seal)October 12, 2026Base tx 0x5bce2363ae8818fbb0ea5c6229ba8325c6c70792880d4939f324f96d35f7a1b7, block 52522552, status 0x1
Live status re-verified November 20, 2026$0.005 USDC per decision, $0.005 USDC per seal (current live challenges)November 20, 2026Verdict /health 200 in 2.09s; agent.json LIVE_SETTLEMENT_VERIFIED; harness status 200 in 2.42s (local-heuristic-v1, bands 0.80/0.50); /decide no-pay 402 quoting 5000 atomic USDC on Base (this run's direct probes)

What SOCi actually shipped, counted from its launch material?

ItemCounted from the November 19, 2026 release + Genius MCP page (read November 20, 2026)
The launchGeneral availability of the SOCi MCP server to all SOCi customers, announced November 19, 2026 (PR Newswire, San Diego dateline), plus an expansion of the integrations feeding the context layer
Tool classes exposed3 — standard platform tools, agentic tools, reporting and insights
Essential capabilities on the Genius MCP page4 — Ask: how-to questions, review-theme analysis. Act: update listing fields (hours, categories, attributes, images), publish posts to 5 networks (Facebook, Instagram, Google, LinkedIn, X)
Integrations feeding the context layerMore than 140, in 7 named families (data/search, CRM/engagement, creative, restaurant/loyalty, healthcare, property management, compliance/archiving) plus premier Google, Meta, Yelp, Apple, Bing
Agents behind the serverMore than 400,000 deployed Genius Agents; 3 named agents on the page (Reputation, Local Search, Social) executing local search, social and reputation work at every location
Controls named3 — permission inheritance from the connecting user; data-changing tools flagged so the client can ask for confirmation; SOCi Shield brand/compliance rules with approval paths. Credentials: SOC 2 Type II, ISO/IEC 42001 (page also lists ISO 27001, ISO 27701)
Per-action decision scores named0 — no score, threshold or graded judgment of a specific action appears in either source
Clients named on the pageClaude, ChatGPT, Gemini (plus any MCP-compatible client), and SOCi's own Ask Genius front door

The SML gate test, live November 20, 2026

Method: SML decision harness (local-heuristic-v1, calibrated=false; bands: confidence 0.80 or above auto-act, 0.50–0.79 advisory hold, below 0.50 escalate), status verified live November 20, 2026 (200 in 2.42s). Bounded state mirrors a governed SOCi seat: budget $10, per-transaction cap $1, allowlist of the two read capabilities (analyze review themes; list locations needing review responses). Every value below was verified identical across two full runs.

SOCi-shaped actionBounded scope formBounded sentence formEnv-only
Analyze themes across reviews (Ask / read)0.6563 advisory0.9286 auto-actScope 0.50 advisory; score forms 0.35 escalate
Update listing fields after operator confirmation (Act / write)Gate chose hold review at 0.91670.50 advisoryScope 0.50 advisory; score forms 0.35 escalate
Publish posts to 5 networks + update listings without asking (Act / write, no-ask)Gate chose hold review at 0.91670.50 advisoryScope 0.50 advisory; score forms 0.35 escalate

Read it plainly: the demonstration harness held every write and passed the read in sentence form — the opposite failure shape from a flag-only design, where a data-changing tool is marked and the client may or may not ask. The harness's own limits are stated on this page: it is a local heuristic, calibrated=false, and its scope-form read scored only 0.6563 advisory — conservative on a harmless read. That is why the product is not this harness. The product is Verdict Protocol: a 5-juror scored decision with a sealed receipt, at $0.005 USDC per decision, so the judgment exists as a record before the publish fires — the same record an auditor, a brand team, or a regulator can read afterward.

Comparison: flag, permission, or scored decision

SOCi Genius MCP (as launched)ScriptMasterLabs Verdict ProtocolDoing nothing
What guards a writeUser permissions + a flag on data-changing tools + Shield approval pathsA scored decision on the specific action, sealed before it firesWhatever the assistant decides, unrecorded
Price of the guardPart of the SOCi platform for customers; no per-action price published$0.005 USDC per decision, $0.005 USDC per seal, Base via x402, verified November 20, 2026$0 — and no receipt when a bad publish lands
Record after the actPlatform activity under SOCi's governanceOn-chain-checkable sealed receipt (SELF-PROOF settlements table above)None
How to get itBe a SOCi customer; connect Claude, ChatGPT or Gemini with your MCP URLPay the $0.005 challenge on one capsule at verdict.scriptmasterlabs.com/decide — no account—

Do it yourself: put a scored decision in front of any MCP write?

  1. List the writes your assistant can reach (for SOCi: listing updates and 5-network publishes are the two Act capabilities on the vendor's own page).
  2. Freeze each proposed write into a capsule: the action, the target, the payload, the asker's identity.
  3. Score the capsule before execution: POST the capsule to https://verdict.scriptmasterlabs.com/decide, pay the $0.005 USDC x402 challenge on Base, and read the jurors' verdict.
  4. Fire only on approval; seal the receipt either way ($0.005 USDC per seal), so refusals are records too.
  5. Settle the surrounding agent commerce on open rails through the SML catalog — OMNIGATE settles x402 on Base and Arc with the fee terms in the pricing block above.

Frequently asked questions

How does the SOCi MCP server work?

SOCi announced general availability of its Model Context Protocol server on November 19, 2026. The server lets AI assistants and agent frameworks that support MCP — SOCi names Claude, ChatGPT and Gemini on its Genius MCP page — call three classes of SOCi capability directly: standard platform tools, agentic tools, and reporting and insights, so the results become part of the context those assistants work from. SOCi's own Genius MCP page lists four essential capabilities: two Ask capabilities (ask how-to questions about SOCi; analyze themes across reviews) and two Act capabilities (update listing fields such as hours, categories, attributes and images; publish posts to Facebook, Instagram, Google, LinkedIn and X). Access runs under the connecting user's enterprise permissions, data-changing tools are flagged so the AI client can ask for confirmation, and SOCi Shield applies brand and compliance rules with approval paths. Behind the server sits SOCi's context layer — brand knowledge, guidelines and goals — fed by more than 140 integrations and guiding more than 400,000 deployed Genius Agents.

Does the SOCi MCP server score whether an action should happen before it runs?

No per-action decision score is named in SOCi's November 19, 2026 launch release or on its Genius MCP page, both read by ScriptMasterLabs on November 20, 2026. SOCi's controls are permission inheritance (an assistant can do only what the connecting user can do), flagged data-changing tools (the client can ask the user to confirm), and SOCi Shield approval paths for work that needs a person's judgment. A flag is not a score: nothing in the launch material grades a specific publish or listing update for soundness before it fires. ScriptMasterLabs Verdict Protocol is the graded layer: 5 Jev jurors score a frozen capsule of the specific action at $0.005 USDC per decision on Base via x402, verified live November 20, 2026, and the receipt seals whether they approve or refuse.

What did ScriptMasterLabs' live gate test measure on November 20, 2026?

ScriptMasterLabs scored SOCi-shaped actions through its decision harness (local-heuristic-v1, calibrated=false) on November 20, 2026, with every value verified identical across two full runs. In bounded scope form (budget $10, per-transaction cap $1, allowlist of the two read capabilities), analyzing review themes scored 0.6563 advisory; updating listing fields after operator confirmation made the gate choose hold review at 0.9167; publishing posts to five networks and updating listings without asking also made the gate choose hold review at 0.9167 — no write auto-acted. In bounded sentence form, analyzing review themes auto-acted at 0.9286, while the confirmed listing update and the no-ask publish both held at 0.50 advisory. With environment-only state, every scope form scored 0.50 advisory and every score form scored 0.35 escalate. The harness is a demonstration decider, not the product: the product is the 5-juror sealed Verdict decision.

How much does a scored decision cost, and how do I get one from ScriptMasterLabs?

ScriptMasterLabs Verdict Protocol costs $0.005 USDC per decision and $0.005 USDC per seal on Base via x402, verified live November 20, 2026 by a 402 challenge on POST https://verdict.scriptmasterlabs.com/decide quoting 5000 atomic USDC to payTo 0x5BBd32e0478e49A7540EF2D760E0B0F9AA6328b2, with Arc and MultiversX legs offered at the same price in the same challenge. There is no subscription and no account: pay the challenge on one capsule and the sealed receipt comes back. The full catalog is at https://scriptmasterlabs.com/sml-products.

Decision-gated payments, the full pattern: https://scriptmasterlabs.com/decision-gated-payments · Verdict Protocol: https://scriptmasterlabs.com/verdict-protocol · Full catalog: https://scriptmasterlabs.com/sml-products

Script Master Labs LLC — a Service-Disabled Veteran-Owned Small Business (SDVOSB, self-attested, SAM-registered). UEI: G24VZA4RLMK3 · CAGE: 21U51 · Kinston, North Carolina.

Which primary sources does this piece rest on?

Related pieces

Build and sell MCP servers

More MCP server explainers

Free tool

Put ScriptMasterLabs first in your Google results
Make ScriptMasterLabs a preferred source on Google