Tengence GEO Agent MCP server

Read from the package source without running it. The installed server may list more.

• article_draft

  Assemble a ready-to-use writing brief for a new article: the matched T1–T7 body skeleton, the pre-writing research-brief template,

• article_export

  Export an article md + brief from the DB to the site data/inbox (for rewriting)

• article_ingest

  Content ingest (single entry): body md + research brief → articles table (CLI canonical orchestration)

• article_list

  List articles (articles table), with status/limit filters

• channel_check

  Validate a title/body against a platform's style rules — the 校验 (validation) half. Deterministic, no content generation.

• channel_list

  List all external content platforms in the syndicate registry: API type (official|cookie|none), status (ready|pending|manual),

• channel_plan_markwrite action

  Update a channel_plan row status (todo | draft | published | paused) and optionally record its draft ids (media ids).

• channel_plan_next

  Per-platform publishing calendar: return the next article to publish for a platform plus all calendar rows

• channel_plan_reconcile

  Reconcile a platform channel_plan with what is ACTUALLY published on that platform (platform=juejin | csdn).

• channel_publishwrite action

  Publish/export to one external platform. Mode A: pass slugs[] and the server reads the DB and runs the platform pipeline

• channel_style_get

  Return the FULL platform style / rewrite rules for ONE platform (wechat / juejin / blog / …).

• channel_taxonomy_list

  Read the cached external-platform taxonomy dictionary (channel_taxonomy) — the platform's OWN categories and tags

• channel_taxonomy_resolve

  Preview how OUR taxonomy maps onto a platform's (article_plan.category/tags → platform category_id/tag_ids) WITHOUT

• channel_taxonomy_sync

  Refresh the cached dictionary of an EXTERNAL platform's own taxonomy (category + tag id/name) into the workspace

• check_articlewrite action

  Publish gate: enforces the editorial rules codified in the "article-writing-standards" standard (citation dual-channel, word count by T1–T7 type, banned words, the three GEO blocks — Summary / Key Takeaways / FAQ / Data Sources — and the research-brief hard check). Read that standard via standards_read before authoring, and run article_draft first to scaffold per-spec.

• csdn_article_deletewrite action

  Delete a CSDN article (blog/phoenix/console/v1/article/del). IRREVERSIBLE — pass confirm=true only after verifying the

• csdn_status

  Read the CSDN blog backend for this site: the draft box and the published list

• db_init

  Explicitly initialize the database (sqlite idempotent table creation / mysql DDL; --drop rebuilds)

• db_status

  Database status: driver, path, schema version, table list, missing tables

• diagnose_site

  Full GEO/SEO site diagnosis: domain (DNS/TLS cert/WHOIS), transport & server fingerprint (CMS/framework/platform/CDN), robots.txt, sitemap, homepage + representative pages (meta, H1..H6 structure, JSON-LD, OG, images/alt, links, mixed content), performance and security checks. Bootstraps the site on first use (url → site key, dots → underscores).

• image_acquire

  Auto image pipeline (search → red-line filter → download → WebP crop → upload to WP media library)

• juejin_article_deletewrite action

  Delete a published Juejin article (article/delete). IRREVERSIBLE — pass confirm=true only after verifying the article id

• juejin_draft_deletewrite action

  Delete a Juejin draft (article_draft/delete). IRREVERSIBLE — pass confirm=true only after verifying the draft id via

• juejin_status

  Read the Juejin (掘金) backend for this site: the draft box (article_draft/list_by_user) and the published list

• monitor_report

  Read monitoring results (latest round or a given run_id)

• monitor_runwrite action

  Run GEO monitoring (one round of site prompts × models; results persisted)

• plan_import

  Import/update the plan table from the site plan directory (idempotent)

• plan_list

  Article plan table list (status/batch/category/node filters)

• plan_mark_statuswrite action

  Update a plan row status (todo/written/queued/published/archived)

• publish_dailywrite action

  Run the daily promotion task (promotes due drafts to publish by plan publish_order; default 1/day).

• publish_draftwrite action

  Publish a draft (default draft → WP; can --status=publish directly, must pass the gate first)

• publish_from_dbwrite action

  Publish an article from the DB to WordPress (--force updates an existing article)

• publish_update_articlewrite action

  Bypass update of an existing article (title/content/status + sync SEO/GEO meta).

• report_writewrite action

  Write a Markdown report into the site data/reports/ directory (path-safe: filename is basenamed and confined to the reports dir). Auto-bootstraps the site on first use.

• search_gsc_inspect

  Query one URL's Google indexing status (URL Inspection API, read-only): verdict, coverageState,

• search_gsc_stats

  Read Google Search Console Search Analytics data: clicks / impressions / CTR / average position,

• search_submit_baiduwrite action

  Submit URLs to Baidu normal inclusion (requires BAIDU_TOKEN / BAIDU_SITE).

• search_submit_gscwrite action

  Submit the sitemap to Google Search Console (soft-fail)

• search_submit_indexnowwrite action

  Submit URLs to IndexNow (requires INDEXNOW_KEY)

• site_init

  Scaffold a site inside the bound workspace: <workspace>/<key>/{config,data/inbox,data/reports,.env} (idempotent, never overwrites existing files)

• site_list

  List the sites inside the bound user workspace (site key, domain, app_id, storage driver). Returns a hint instead when no workspace is bound yet.

• site_status

  Site status: config paths, .env readiness, DB driver and SQLite init state

• standards_list

  List the generic writing & GEO standards shipped with the engine (titles, whether a site-specific supplement exists).

• standards_read

  Read a generic standard document (base + any site-specific supplement merged). Names are repository-relative without `.md`,

• util_ping

  Connectivity self-check: SDK version, driver, internal data directory, bound workspace and site count

• webmaster_bing_status

  Read Bing Webmaster console data (verified sites / URL submission quota / query stats / crawl issues). Requires BING_WEBMASTER_API_KEY in the site .env. Note: Bing trimmed its JSON API on 2026-08-31 (GetPages/GetSitemaps/GetTrafficStats/GetUrlSubmissionStatus now 404).

• webmaster_bing_submitwrite action

  Write to Bing Webmaster: submit URL(s) (comma-separated = batch, ≤10000 per call). Requires BING_WEBMASTER_API_KEY in the site .env.

• wechat_article_deletewrite action

  Delete a published article (freepublish/delete, article_id from wechat_status published). IRREVERSIBLE — verify the

• wechat_draft_publishwrite action

  Publish a draft box media_id to the account homepage via freepublish/submit (NO push to followers — the draft is

• wechat_mass_previewwrite action

  Send a draft (media_id from the draft box) to one user as a preview (message/mass/preview). Requires a verified

• wechat_mass_sendwrite action

  Mass-send (PUSH to followers) a draft via message/mass/sendall (all followers or one tag) or message/mass/send

• wechat_mass_status

  Query a mass-send task status (message/mass/get, msg_id from wechat_mass_send).

• wechat_stats

  Read official-account statistics from the WeChat backend (datacube/*, served WITHOUT the /cgi-bin/ prefix —

• wechat_status

  Read the WeChat official-account backend: the draft box (draft/batchget — media_id + titles) and the mass-sent list

• wechat_sync_progress

  Reconcile the channel_plan calendar with the real WeChat backend and auto-fix the DB: draft rows whose media_id is

• workspace_use

  Bind the user workspace directory (call this first): all site config, credentials and output files live under it. Ask the user which directory to use if it was not mentioned; `~` is supported and expanded here.

• Code scan5 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identitynamespace and repository owner differ; GitHub account older than a year6/10

Tengence GEO Agent: common questions

Is Tengence GEO Agent MCP server safe?

Yes, by our scan: it is graded A (89/100). Read the Tengence GEO Agent safety report

How do I install Tengence GEO Agent?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Tengence GEO Agent need an API key?

No secret keys are declared. It reads 3 settings from the environment.

Is Tengence GEO Agent maintained?

The last commit was 11 days ago (2026-10-02). The latest release is v0.1.2.

What can I use instead of Tengence GEO Agent?

Servers from other publishers that do the same job: Frase SEO MCP server, Blawgy MCP server and AfterLaunch: the agentic growth marketing engine MCP server. Compare all Tengence GEO Agent alternatives.