Skip to content

MCP servers › io.github.sorzio › sorzio

MCP server · registry snapshot 2026-11-04 · last tested 2026-11-04

sorzio MCP server

Registry name io.github.sorzio/sorzio

by sorzio · GitHub account (the registry's namespace rule)repository: same ownerSource ↗Website ↗

B2B web & LinkedIn enrichment, email verification, ICP scoring & AI copy for up to 25,000 leads. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-11-04version 1.0.0streamable HTTP41 tools

Summary

io.github.sorzio/sorzio is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the GitHub account sorzio. Its linked repository, github.com/sorzio/sorzio-mcp, belongs to the same GitHub account. On 2026-11-04 ProtocolProbe connected to it in read-only mode and read its inventory: 41 tools, 2 resources and 6 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

  • met: Registry entry is active and says how to run it
  • met: Source repository link opens
  • met: Repository is not archived
  • met: Code pushed to the repository in the 90 days before our check
  • not met: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 1 star (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Repository
public
Tools
41
Last tested
2026-11-04

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-04 (www.sorzio.com), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.0.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 12 tools whose name or declaration suggests they change data (create_list, add_rows, delete_list, purge_lists, save_prompt and 7 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-04.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-04
Mode
read-only (no tool calls)
Latest version
1.0.0, published 2026-11-03 (registry, as of the 2026-11-04 snapshot)
First listed version
2026-11-03 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-11-04
Package and repository
checked 2026-11-04
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-03, listed on 2026-11-04 with version 1.0.0 (published 2026-11-03).

Source: the official MCP Registry list on 2026-11-03 and on 2026-11-04.

What it is

What does this server offer?

Observed inventory
41tools
2resources
6prompts

None of its 41 tools are described as changing anything. For 41 the reading was uncertain, so no mark is shown.

  • “Start here when Sorzio is new in this chat, or when the user asks for the quickest way to enrich a list or CSV of leads/companies (up to 25,000 rows), match or score companies against their ICP, veri…”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • open_dashboardon 2 other servers

    “The workspace at a glance.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • “Workspace name, current balance, auto-recharge settings and which bring-your-own-key AI providers are set up.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • “AI models you can use with Sorzio, featured models first, then by provider and price, with price per 1,000 rows and whether they support web search or reasoning.”

    Publisher declares: read-only yes · open-world no

    5 inputs
    • searchstring“Filter by text in the id or name.”
    • providerstring
    • supports_web_searchboolean“When true, only return models that support live web search (such as perplexity/sonar, OpenAI, Anthropic, Google Gemini, and xAI Grok).”
    • limitinteger“Defaults to 50.”
    • kindstring
  • estimate_coston 60 other servers

    “Estimate what an AI, verify, scrape or Flow run would cost, for a number of rows, for a list (for a Flow too, where Flows on lists are on), or (for a Flow) for the rows on a connected sheet.”

    Publisher declares: read-only yes · open-world no

    17 inputs, 1 required
    • kindstringrequired
    • rowsinteger“Row count.”
    • list_idstring“Use this list's row count instead of rows (for kind flow too, where Flows on lists are on).”
    • modelstring“Model id from list_models.”
    • promptstring
    • system_promptstring
    • reasoning_effortstring or integer
    • web_searchboolean
    • verify_providerstring
    • scrape_providerstring
    • enrich_typestring
    • flow_idstring“Required for kind flow.”
    • spreadsheet_idstring“Kind flow only, instead of rows: the sheet id or full docs.google.com URL.”
    • tabstring“Kind flow only.”
    • header_rowinteger“Kind flow only.”
    • input_columnsobject“Kind flow only.”
    • only_rows_whereobject“When estimating a list run, count only the rows that match this filter.”
  • “Your recent AI, verify and scrape runs in this workspace, newest first, with rows, what each run charged and where it was started (source: mcp or addon).”

    Publisher declares: read-only yes · open-world no

    4 inputs
    • typestring
    • sourcestring“Only runs started through this agent connection ("mcp") or from the Google Sheets add-on ("addon").”
    • limitinteger
    • cursorstring
  • “List active, non-expired Hosted Lists in this workspace (newest first, up to 100, default 25), returning list_id, name, row_count, hidden_row_count, columns, output_columns, created_at, expires_at, a…”

    Publisher declares: read-only yes · open-world no

    1 input
    • limitinteger“Max active lists to return (1 to 100, default 25).”
  • “Hand rows to Sorzio.”

    Publisher declares: read-only no · destructive no · open-world no

    5 inputs, 1 required
    • namestringrequired
    • columnsarray“Column names, in order.”
    • rowsarray“Up to 500 rows; one value per column, in column order.”
    • uploadobject“Ask for a CSV upload URL instead of inline rows.”
    • google_sheet_urlstring“Import rows directly from a docs.google.com/spreadsheets/d/...”
  • “Append up to 500 rows to an inline list (5,000 inline rows in total).”

    Publisher declares: read-only no · destructive no · open-world no

    2 inputs, 2 required
    • list_idstringrequired“The list_id returned by create_list.”
    • rowsarrayrequired
  • “Page through a list's rows (up to 200 per call, and at most about 100,000 characters), optionally only some columns.”

    Publisher declares: read-only yes · open-world no

    6 inputs, 1 required
    • list_idstringrequired“The list_id returned by create_list.”
    • cursorstring
    • limitinteger
    • columnsarray
    • full_textboolean“Return one row with its cells uncut, up to 100,000 characters.”
    • rowinteger“With full_text: the row number to read, from 1.”
  • “Build a CSV of the whole list.”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • list_idstringrequired“The list_id returned by create_list.”
  • “Immediately delete one Hosted List and remove its stored CSV and archive files from this workspace.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input, 1 required
    • list_idstringrequired“The list_id returned by create_list.”
Show 29 more tools
  • purge_lists

    “Purge idle Hosted Lists and delete their stored files in this workspace.”

    Publisher declares: read-only no · destructive yes · open-world no

    1 input
    • modestring“Purge 'all' idle lists (default) or only 'temporary' non-Forever lists.”
  • “Google Sheets you have opened with the Sorzio add-on (up to 25), with their tabs.”

    Publisher declares: read-only yes · open-world yes

    Takes no inputs.

  • “Read the header row and up to 50 rows from a connected Google Sheet (sequentially from start_row or specific row_numbers).”

    Publisher declares: read-only yes · open-world yes

    8 inputs, 1 required
    • spreadsheet_idstringrequired“Sheet id, or the full docs.google.com URL.”
    • tabstring“Tab name.”
    • header_rowinteger“Row number of the header.”
    • rowsinteger“Rows to read below the header (or from start_row).”
    • start_rowinteger“1-based sheet row number to start reading data rows from.”
    • row_numbersarray“Specific 1-based sheet row numbers to inspect (e.g.”
    • columnsarray“Projection of column header names or A1 column letters to include (e.g.”
    • max_cell_charsinteger“Per-cell character limit override before [cut: ...].”
  • “Your saved AI prompts (shared ones and your own), plus your favourite and recent prompts from runs in the Sorzio add-on's Library: title, prompt, system prompt, model, last run date and whether it is…”

    Publisher declares: read-only yes · open-world no

    2 inputs
    • cursorstring“next_cursor from the previous call, for more saved prompts.”
    • limitinteger“Saved prompts per page.”
  • “One prompt in full: a saved prompt by prompt_id, or a favourite or recent one by history_id (from list_prompts).”

    Publisher declares: read-only yes · open-world no

    2 inputs
    • prompt_idstring“A saved prompt's id from list_prompts.”
    • history_idstring“A favourite or recent prompt's history_id from list_prompts.”
  • save_prompt

    “Save a new prompt (action create: name and prompt_template) or change one of yours (action update: prompt_id and the fields to change).”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    8 inputs, 1 required
    • actionstringrequired
    • prompt_idstring“update: the prompt to change.”
    • namestring
    • prompt_templatestring
    • system_instructionstring or null
    • modelstring“Model id from list_models.”
    • categorystring or null
    • is_sharedboolean
  • delete_prompton 2 other servers

    “Delete one of your saved prompts.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • prompt_idstringrequired
  • preview_prompt

    “Run a prompt on the first 1 to 3 rows of a list or connected sheet and see the real output and cost before a full run.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    12 inputs, 2 required
    • request_idstringrequired
    • targetobjectrequired
    • promptstring
    • prompt_idstring
    • system_promptstring
    • modelstring“Model id from list_models.”
    • temperaturenumber
    • reasoning_effortstring or integer
    • web_searchboolean“Enable live web search / online grounding per row (requires a model with supports_web_search: true from list_models, or use perplexity/sonar which searches the…”
    • rowsinteger
    • sample_strategystring“Sampling strategy when row_numbers is omitted: 'first_n' (default), 'random', or 'diverse'.”
    • row_numbersarray“Explicit 1-based row numbers to test the prompt on.”
  • run_ai

    “Run an AI prompt once per row of a list or connected sheet.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    15 inputs, 2 required
    • request_idstringrequired“A new UUID for each run.”
    • targetobjectrequired“A list from create_list, or a Google Sheet connected through the Sorzio add-on.”
    • promptstring
    • prompt_idstring“A saved prompt's id from list_prompts; supplies the text, system instruction and model.”
    • system_promptstring
    • modelstring“Model id from list_models.”
    • temperaturenumber
    • reasoning_effortstring or integer
    • web_searchboolean“Enable live web search / online grounding per row (requires a model with supports_web_search: true from list_models, or use perplexity/sonar which searches the…”
    • verify_outputboolean“Verify each generated row with Jev and auto-retry once if ungrounded claims or AI cliches are detected.”
    • output_namestring“List runs: the name of the new column this run adds to the list.”
    • only_rows_whereobject“Run just the rows that match (works on both lists and Google Sheets).”
    • overwriteboolean“Sheet runs: replace cells that already have a value.”
    • test_rowsinteger“Run only the first 1 to 50 selected rows, to try the run first.”
    • confirm_tokenstring“Only after a needs_confirmation result: the confirm_token from it, once the user said yes.”
  • run_verify

    “Check whether each email in a column is deliverable.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    9 inputs, 3 required
    • request_idstringrequired“A new UUID for each run.”
    • targetobjectrequired“A list from create_list, or a Google Sheet connected through the Sorzio add-on.”
    • email_columnstringrequired“The list column or sheet header that holds the email.”
    • providerstring“Leave omitted to use the default email verifier automatically.”
    • output_namestring“List runs: the name of the new column this run adds to the list.”
    • only_rows_whereobject“Run just the rows that match (works on both lists and Google Sheets).”
    • overwriteboolean“Sheet runs: replace cells that already have a value.”
    • test_rowsinteger“Run only the first 1 to 50 selected rows, to try the run first.”
    • confirm_tokenstring“Only after a needs_confirmation result: the confirm_token from it, once the user said yes.”
  • run_scrape

    “Fetch the web page (or LinkedIn company page) for each URL in a column and return its text.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    14 inputs, 2 required
    • request_idstringrequired“A new UUID for each run.”
    • targetobjectrequired“A list from create_list, or a Google Sheet connected through the Sorzio add-on.”
    • url_columnstring“The list column or sheet header that holds the URL, domain, or UK company number.”
    • input_columnstring“Alias for url_column.”
    • providerstring“Leave omitted for automatic routing (LinkedIn company URLs, LinkedIn personal profile URLs linkedin.com/in/..., UK Companies House numbers, or website waterfal…”
    • typestring“Alias for provider (enrichment capability mode).”
    • enrich_typestring“Alias for provider (enrichment capability mode).”
    • subpagesarray“Optional standard website subpages to discover and merge into the same cell at $0 extra cost (up to 3 fetched per domain: about, products, case_studies, pricin…”
    • force_refreshboolean
    • output_namestring“List runs: the name of the new column this run adds to the list.”
    • only_rows_whereobject“Run just the rows that match (works on both lists and Google Sheets).”
    • overwriteboolean“Sheet runs: replace cells that already have a value.”
    • test_rowsinteger“Run only the first 1 to 50 selected rows, to try the run first.”
    • confirm_tokenstring“Only after a needs_confirmation result: the confirm_token from it, once the user said yes.”
  • “Status of a run you started: row counts, progress, what it cost, the most common error codes, and (for a list run) when the list expires.”

    Publisher declares: read-only yes · open-world no

    2 inputs, 1 required
    • run_idstringrequired“The run_id a run tool returned.”
    • wait_secondsinteger“Wait up to this many seconds (0 to 50) for the run to end before answering.”
  • “Stop a queued or running run.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • run_idstringrequired“The run_id a run tool returned.”
  • retry_failed

    “Run again only the rows of a finished run that failed, with the same prompt and model.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    7 inputs, 2 required
    • request_idstringrequired“A new UUID for each run.”
    • run_idstringrequired“The finished run whose failed rows to re-run.”
    • temperaturenumber
    • reasoning_effortstring or integer
    • web_searchboolean
    • force_refreshboolean“Scrape runs: skip cached pages.”
    • confirm_tokenstring“Only after a needs_confirmation result: the confirm_token from it, once the user said yes.”
  • get_run_rows

    “Read processed rows directly from a run (batch_job_rows), including Google Sheet runs that hit sheet_too_large or have unwritten_rows.”

    Publisher declares: read-only yes · destructive no · open-world no

    6 inputs, 1 required
    • run_idstringrequired“The run_id of the batch run.”
    • offsetinteger“0-based offset into matching rows.”
    • limitinteger“Max rows to return (1 to 200).”
    • statusstring“Filter rows by outcome status.”
    • unwritten_onlyboolean“When true, only return rows where written_to_sheet_at is null.”
    • max_cell_charsinteger“Truncate each row output to at most this many characters (50 to 20,000).”
  • “Export processed rows from a run as RFC 4180 CSV (row,status,output,error_code) or JSON array, capped at 100 KB per page with next_offset pagination.”

    Publisher declares: read-only yes · destructive no · open-world no

    4 inputs, 1 required
    • run_idstringrequired“The run_id of the batch run.”
    • formatstring“Output format: csv or json.”
    • unwritten_onlyboolean“When true, only export rows where written_to_sheet_at is null.”
    • offsetinteger“0-based row offset for pagination.”
  • “Your workspace's Flows: saved multi-step pipelines (scrape, verify, AI, filter and gate steps) that run over a Google Sheet.”

    Publisher declares: read-only yes · open-world no

    1 input
    • include_archivedboolean“Include archived Flows.”
  • “One Flow with its version 2 spec, the sheet columns it reads (inputs), the columns it writes (outputs) and its variables.”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • flow_idstringrequired
  • “Create a Flow, change one or copy one.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    5 inputs, 1 required
    • actionstringrequired
    • flow_idstring“update and duplicate: the Flow to change or copy.”
    • namestring“create (required) and update.”
    • descriptionstring or null
    • specobject“create (required) and update: the version 2 Flow spec as an object, not a string.”
  • “Archive a Flow: it no longer shows in list_flows (unless include_archived) and cannot be run.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • flow_idstringrequired
  • “Run a saved Flow on a hosted list (target.list_id, from create_list) or on a Google Sheet connected through the Sorzio add-on (target.sheet, or spreadsheet_id and the other sheet fields).”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    14 inputs, 2 required
    • request_idstringrequired“A new UUID for each run.”
    • flow_idstringrequired“A Flow's flow_id from list_flows.”
    • targetobject“Where the Flow runs: a list from create_list, or a Google Sheet connected through the Sorzio add-on.”
    • spreadsheet_idstring“Sheet runs without target: the sheet id, or the full docs.google.com URL.”
    • tabstring“Sheet runs without target: tab name.”
    • header_rowinteger“Sheet runs without target: row number of the column names.”
    • start_rowinteger“Sheet runs without target: first row to run.”
    • end_rowinteger“Sheet runs without target: last row to run.”
    • test_rowsinteger“Run only the first 1 to 100 rows (on a sheet from start_row, on a list its first rows no Flow has hidden), to try the Flow.”
    • variablesobject“Values for the Flow's variables, by key.”
    • input_columnsobject“Map a Flow input token (without the braces) to a list column or sheet header name, for names that do not match the token.”
    • overwriteboolean“On a sheet, replace filled cells in existing columns named like the Flow's outputs; on a list, add the Flow's values to outputs the list already has.”
    • only_emptyboolean“On a sheet, reuse existing output columns and run each step only on rows where that step's output cell is still blank or failed (#ERROR / Failed:), skipping ro…”
    • confirm_tokenstring“Only after a needs_confirmation result: the confirm_token from it, once the user said yes.”
  • get_flow_run

    “Status of a Flow run in your workspace: rows per step, totals, what it has charged so far, and why it failed if it did.”

    Publisher declares: read-only yes · open-world no

    3 inputs, 1 required
    • flow_run_idstringrequired“The flow_run_id run_flow returned.”
    • wait_secondsinteger“Wait up to this many seconds (0 to 50) for the run to end before answering.”
    • include_rowsboolean“With true, a finished run of at most 10 rows (a test run) also returns row_results: each row's inputs, every step's value or error, and the gate that stopped t…”
  • cancel_flow_run

    “Stop a queued or running Flow run.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 1 required
    • flow_run_idstringrequired“The flow_run_id run_flow returned.”
    • sweep_dispositionsboolean“When true, also move or delete rows that already have a rejected gate verdict on the sheet.”
  • list_scheduleson 22 other servers

    “Your workspace's schedules: which Flow runs on which sheet and tab, how often, and when it runs next.”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • create_scheduleon 15 other servers

    “Schedule a Flow on a connected Google Sheet.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    13 inputs, 7 required
    • flow_idstringrequired“The Flow to run, from list_flows.”
    • spreadsheet_idstringrequired“The sheet id, or the full docs.google.com URL.”
    • tabstringrequired“The tab to run on.”
    • header_rowinteger“Row number of the column names.”
    • input_columnsobject“Map a Flow input token (without the braces) to a header name, for headers that do not match the token by name.”
    • namestringrequired“A name for the schedule.”
    • frequencystringrequired
    • days_of_weekarray“weekly: 0 is Sunday, 6 is Saturday.”
    • day_of_monthinteger“monthly: 1 to 28.”
    • time_of_daystringrequired“24-hour HH:MM, like 09:00.”
    • timezonestringrequired“IANA timezone, like Europe/Paris.”
    • watermark_columnstring“A header name.”
    • overwriteboolean“Replace filled cells in existing columns named like the Flow's outputs.”
  • delete_scheduleon 14 other servers

    “Delete a schedule so no further runs start from it.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • schedule_idstringrequired“A schedule_id from list_schedules.”
  • list_page_templates

    “List the 4 executive outbound micro-page archetypes (Market & Buying-Signal Map, 1-Page Outbound & Funnel Teardown, Competitor Wedge & Gap Matrix, and Pipeline & Signal ROI Blueprint), their recommen…”

    Publisher declares: read-only yes · open-world no

    Takes no inputs.

  • publish_list_pages

    “Publish personalized outbound micro-pages from a Hosted List (list_id) or connected Google Sheet (spreadsheet_id plus column letter output_column), writing each row's hosted URL (/hosted/<org>/<templ…”

    Publisher declares: read-only no · destructive no · open-world yes

    18 inputs
    • list_idstring“Hosted List UUID (pass either list_id or spreadsheet_id).”
    • spreadsheet_idstring“Google Sheet ID or URL (pass either list_id or spreadsheet_id).”
    • tabstring“Optional tab name when publishing from a Google Sheet.”
    • header_rowinteger“Header row number on a Google Sheet (default 1).”
    • output_columnstring“Output column name on a list (default matches template, e.g.”
    • header_namestring“Optional header label written to a Google Sheet output column.”
    • step1_hook_columnstring“Optional column name (on a list) or column letter (on a sheet) to write a zero-link Step 1 permission hook.”
    • template_idstring“Page archetype ID (default empra-market-map-v1).”
    • template_slugstring“Optional template handle (e.g.”
    • themestring“Visual theme mode: obsidian (dark) or editorial (light).”
    • sender_company_namestring“Sender brand name displayed in the page header and CTA.”
    • accent_color_hexstring“Brand accent hex color, such as #10B981.”
    • cta_labelstring“Primary CTA button label.”
    • cta_urlstring“Booking or calendar CTA URL (https://).”
    • custom_domainstring“Verified custom CNAME subdomain (e.g.”
    • slack_webhook_urlstring“Optional HTTPS Slack webhook URL for high-intent engagement alerts.”
    • alert_emailstring“Optional alert email for low-balance or high-intent page events.”
    • max_rowsinteger“Maximum rows to publish in one call (1 to 1000).”
  • get_page_analytics

    “Read workspace-wide or list_id-scoped hosted page engagement analytics, including human_views, bot_views (security scanners filtered out), engaged_pages, cta_clicks, avg_dwell_seconds, and top engage…”

    Publisher declares: read-only yes · open-world no

    2 inputs
    • list_idstring“Optional Hosted List UUID to scope analytics to one list.”
    • limitinteger“Maximum top engaged pages to return (1 to 50, default 20).”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-04.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
76% of 195
Tools with a description
100% of 41
Typical description length
593 characters

The tool set

Counted from the listing

Tools
41
Size of the list
about 19,232 tokens for an agent to load (characters ÷ 4)
Naming
41 of 41 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 41 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-04 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://www.sorzio.com/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "sorzio": {
      "url": "https://www.sorzio.com/api/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "sorzio": {
      "type": "http",
      "url": "https://www.sorzio.com/api/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"sorzio","type":"http","url":"https://www.sorzio.com/api/mcp"}'
Claude Code
claude mcp add --transport http sorzio https://www.sorzio.com/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "sorzio": {
      "type": "streamableHttp",
      "url": "https://www.sorzio.com/api/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "sorzio": {
      "httpUrl": "https://www.sorzio.com/api/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.sorzio]
url = "https://www.sorzio.com/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "sorzio": {
      "url": "https://www.sorzio.com/api/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://www.sorzio.com/api/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint www.sorzio.com/api/mcpSession openedmatchesour test · 2026-11-04
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-04
Repository github.com/sorzio/sorzio-mcpOpens publiclymatchesapi.github.com · 2026-11-04

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
io.github.sorzio
GitHub owner
an organization (sorzio)
Repository
github.com/sorzio/sorzio-mcp
Stars
1
Repository age
0–30 days
Last push
0–30 days ago
Archived
no
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-11-04; security policy read from GitHub · 2026-11-04.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 1 star (ranked from 10)
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • MetSource repository link opensThe linked GitHub repository is public.
  • MetRepository is not archivedNot archived.
  • MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
  • Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-04 (security policy 2026-11-04). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about io.github.sorzio/sorzio

Answered from the data above

Who publishes io.github.sorzio/sorzio?

The registry ties the namespace io.github.sorzio to the GitHub account sorzio; only its owner can publish under it. Its linked repository, github.com/sorzio/sorzio-mcp, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.

Is io.github.sorzio/sorzio safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.sorzio/sorzio need an API key or sign-in?

It opened a session without any credential on 2026-11-04. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.sorzio/sorzio been security tested?

Partly. 4 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Does io.github.sorzio/sorzio publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of io.github.sorzio/sorzio?

In github.com/sorzio/sorzio-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-04
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: exercised
  13. Fake assistant turns: not run · an error was returned
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

4 exercised12 not run (reason given)2 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 4
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server returned an error when its prompts were read.not run · an error was returned
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 2
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-11-04, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,425 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 41 tools, 2 resources, 6 prompts.
  4. 10,540 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added in a later update
listed 2026-11-04; not classified yet
Pricing modelAI-classified
pending: added in a later update
the website is not read yet
Programming language
not stated
GitHub detects no source language in this repository (docs-only or empty)
Hosting type
registry · 2026-11-04
MCP capability
prompts, resources, tools
our test · 2026-11-04
Transport
streamable HTTP
registry · 2026-11-04
Required credentials
none declared
registry · 2026-11-04 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-04
Lifecycle status
registry · 2026-11-04
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
owner: an organization · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-11-04
Maintenance
api.github.com · 2026-11-04
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-04

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.sorzio/sorzio: MCP server record.” Data checked 2026-11-04. https://protocolprobe.com/mcp/servers/io.github.sorzio/sorzio

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 4 of 5 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.sorzio/sorzio)](https://protocolprobe.com/mcp/servers/io.github.sorzio/sorzio)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology