Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add localseodata/mcp-server --skill local-seo-datagit clone --depth 1 https://github.com/localseodata/mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/localseodata/mcp-server/local-seo-data)<a href="https://agentmods.dev/skills/localseodata/mcp-server/local-seo-data"><img src="https://agentmods.dev/badge/skills/localseodata/mcp-server/local-seo-data/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/localseodata/mcp-server/local-seo-data"><img src="https://agentmods.dev/badge/skills/localseodata/mcp-server/local-seo-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.00645 |
| Opus 5.5 | $0.00046 | $0.00258 |
| Sonnet 5.5 | $0.00023 | $0.00129 |
| Haiku 4.5 | $0.00011 | $0.00064 |
Grade A, and why
local-seo-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local SEO Data
The localseodata MCP server bundled with this plugin looks up public local search
data for any business and market. It acts as the signed-in Local SEO Data account
and charges that account's credits per call. The server sends its own tool-selection
guide when it connects; follow it. The rules below are the ones that matter most.
Before you act
- Check the balance first on multi-step work.
get_balanceis free. Estimate the total cost before a chain of calls and warn the user if it is more than half their balance. - Resolve the location when it is ambiguous. Most tools take a natural location
such as
Austin, TX. If a tool returns nothing for a place, calllocation_search(free) and retry with the exact format it returns. - Reuse what was already bought. Before re-running a lookup to see whether
something changed, search
history_searchand read the stored answer withhistory_get. Both are free. - Confirm before expensive tools.
local_audit,citation_auditandgeogrid_scancost 50 credits or more. Say the cost and get a yes first. - Pick the cheapest tool that answers.
local_pack(2 credits) answers "who ranks for X in Y"; a fulllocal_auditis not needed for that.
Reading results
- Rankings are non-personalized. They can differ from what the user sees in their own browser, so say so when you present them.
- A question about how often an AI names a business is a question about a rate.
Use
ai_sampleand collect it withai_sample_status(free) instead of a singleai_modeorai_scrapercall. - Do not decide by string comparison whether an AI answer named a business. Pass
the answer's businesses to
ai_matchwith the target's name and location. - For chains, get the store's
place_idfrombusiness_profilefirst and pass it to the review tools.
Scope
Every tool is read-only. Local SEO Data cannot reply to reviews, edit a Business Profile or change any account. It returns public business data only, never personal information about reviewers or other private individuals.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 53 lines · 114 tokens per session scan A 8f5d95e1c15a
local-seo-data is a skill published in the GitHub repository localseodata/mcp-server (3 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 645 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-11.
local-seo-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| local-seo-datalocalseodata/mcp-server | Skill | 3 | yesterday | MIT | A | 114 | Claude Code, Codex |
| seo-audit-reportIamRamgarhia/All-In-One-Free-SEO-Tool | Skill | 126 | 13d ago | MIT | A | 38 | Claude Code |
| seo-fix-passIamRamgarhia/All-In-One-Free-SEO-Tool | Skill | 126 | 13d ago | MIT | A | 38 | Claude Code |
| seo-client-setupIamRamgarhia/All-In-One-Free-SEO-Tool | Skill | 126 | 13d ago | MIT | A | 34 | Claude Code |
| seo-keyword-planIamRamgarhia/All-In-One-Free-SEO-Tool | Skill | 126 | 13d ago | MIT | A | 32 | Claude Code |
| seo-task-runnerIamRamgarhia/All-In-One-Free-SEO-Tool | Skill | 126 | 13d ago | MIT | A | 42 | Claude Code |
| local-falcon-mcplocal-falcon/mcp | Skill | 26 | yesterday | MIT | A | 44 | Claude Code |