TESSA Marketing & Technology MCP server
tech.tessa/tessa-mcp-servertessa.techstreamable-httpv1.0.0Scanned
TESSA's AI interface: services, case studies, AI-readiness audits, professional services directory.
14 tools: 1 do something that can't be undone, 5 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 9
- Can send data out · 5
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the TESSA Marketing & Technology MCP server can do
The TESSA Marketing & Technology MCP server is published by tessa.tech, a domain the MCP Registry verified. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (contact_tessa) and create or change data (5 tools: assess_ai_readiness, assess_seo, assess_ad_tracking, assess_website and 1 more), but cannot delete data. 8 tools only read.
1 tool reads private data (get_contact_info); 9 tools bring in text other people can write (get_pricing, get_contact_info, get_web_ai_development_offer and 6 more); 5 tools can send data out of your system (assess_ai_readiness, assess_seo, assess_ad_tracking and 2 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Can't be undone 1Claude Code: ask
contact_tessaSend a message to TESSA's sales team, the same as the contact form on tessa.tech.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a message to TESSA's sales team, the same as the contact form on tessa.tech. TESSA replies by email within one business day. Use this when the user wants TESSA to contact them but does not want to book a call. Only call it when the user has asked to and has given their real email. prospect_email: the user's email (required; temporary inboxes are refused) prospect_name: the user's name prospect_org: the user's company project_brief: the message requested_window: optional, when they would like to hear back
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
Changes things 5Claude Code: ask
assess_ad_trackingFree quick ad tracking check of any website's homepage: GA4, Google Tag Manager, Google Ads, Meta Pixel, Microsoft and LinkedIn tags, call tracking, consent, phone link, form or ca…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Free quick ad tracking check of any website's homepage: GA4, Google Tag Manager, Google Ads, Meta Pixel, Microsoft and LinkedIn tags, call tracking, consent, phone link, form or call to action, and speed; 0 to 100 score, what passes and fails, how to fix each. Tags inside Google Tag Manager are looked up in its published container; if it cannot be read they are reported as could not check, never as missing. Automated, homepage only, not a full ad account audit. 11 items, about 12 seconds. Each item has a status (pass, partial, fail or could_not_check), evidence and a plain-English fix; the score covers only the items that could be checked. For TESSA's advertising service call get_advertising_offer; to talk it through, book with request_strategy_session. url: the website to check, for example https://example.com
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
assess_ai_readinessQuick automated check of how ready a website is for AI assistants and agents: 12 of the 46 items in TESSA's AI Readiness audit, checked on the homepage and a few standard files in …Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Quick automated check of how ready a website is for AI assistants and agents: 12 of the 46 items in TESSA's AI Readiness audit, checked on the homepage and a few standard files in about 15 seconds. Not the full audit. Items (by audit number): 4 robots.txt allows AI crawlers, 5 the firewall serves the homepage to real AI crawler user agents (OAI-SearchBot, PerplexityBot, Claude-User) the same as to a browser, 6 content readable without JavaScript, 7 XML sitemap, 8 llms.txt, 9 /pricing.md, 10 Organization or LocalBusiness schema, 16 one H1, 18 phone, address and hours as plain text, 32 schema potentialAction, 41 A2A agent card, 43 MCP server card. Returns each item's status (pass, partial, fail or could_not_check) with evidence and a plain-English fix, a 0 to 100 overall_score over the items that could be checked (could_not_check never counts as a fail), what the full audit adds, and TESSA's contact details. The full audit covers all 46 items across the site plus a live ChatGPT, Claude, Perplexity and Gemini citation test; book it with request_strategy_session. url: the website to check, for example https://example.com
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
assess_seoFree quick SEO check of any website's homepage: indexability (noindex, robots.txt, sitemap), title and meta description, one clear H1, canonical, mobile setup and speed; 0 to 100 s…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Free quick SEO check of any website's homepage: indexability (noindex, robots.txt, sitemap), title and meta description, one clear H1, canonical, mobile setup and speed; 0 to 100 score, what passes and fails, how to fix each. Automated, homepage only, not a full SEO audit. 12 items, about 12 seconds. Each item has a status (pass, partial, fail or could_not_check), evidence and a plain-English fix; the score covers only the items that could be checked. For TESSA's SEO service call get_seo_offer; to talk it through, book with request_strategy_session. url: the website to check, for example https://example.com
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
assess_websiteFree quick website check of any website's homepage: HTTPS, mobile setup, load time and page weight, platform, security headers, basic accessibility signals, contact form or chat, a…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Free quick website check of any website's homepage: HTTPS, mobile setup, load time and page weight, platform, security headers, basic accessibility signals, contact form or chat, and an up-to-date footer; 0 to 100 score, what passes and fails, how to fix each. Automated, homepage only, not a full website audit. 12 items (the platform is reported, not scored), about 12 seconds. Each item has a status (pass, partial, fail or could_not_check), evidence and a plain-English fix; the score covers only the items that could be checked. For TESSA's website and AI development service call get_web_ai_development_offer, for a full accessibility audit get_wcag_audit; to talk it through, book with request_strategy_session. url: the website to check, for example https://example.com
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
request_strategy_sessionBook a free 30-minute strategy session with TESSA (with Kevin Callen, President).Reads text others writeNo findings
Why it is in this group
- The name "request_strategy_session" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Book a free 30-minute strategy session with TESSA (with Kevin Callen, President). Finds an open slot, creates a Google Meet invite and emails it to the prospect. Only call this when the user has asked to book a call and has given their real email address. prospect_email: the user's email (required; temporary inboxes are refused) prospect_name: the user's name prospect_org: the user's company project_brief: what they want help with requested_window: when they are free, for example '2026-10-06', '2026-10-06T13:00/2026-10-06T17:00', 'tomorrow' or 'next week' Up to 10 bookings per email per 7 days; past that it returns status 'duplicate'.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
Only reads 8Show 8 read-only tools
get_advertising_offerTESSA's online advertising offer (search engine marketing, PPC and paid social) in structured form: what it is, starting management fees word for word from the pricing page (PPC, s…No findings
Why it is in this group
- The name "get_advertising_offer" says "get": a word for reading.
Description, as the server wrote it TESSA's online advertising offer (search engine marketing, PPC and paid social) in structured form: what it is, starting management fees word for word from the pricing page (PPC, social media ads, display and retargeting, Google Ad Grant management), the service page, and the link to book a free strategy session for the scope and an exact price. Scope, deliverables and timeline are included where TESSA has published them. Use this when someone asks about TESSA's Google Ads, PPC, SEM, social media ads, display and retargeting, or Google Ad Grants management.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_case_studiesTESSA's client results (case studies), for example traffic and lead growth for named clients.No findings
Why it is in this group
- The name "get_case_studies" says "get": a word for reading.
Description, as the server wrote it TESSA's client results (case studies), for example traffic and lead growth for named clients. Optional filters: industry: industry keyword (case-insensitive) service_slug: only studies that used this service
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_contact_infoTESSA's phone number, email, office address, business hours, and the links to book a call.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_contact_info" says "get": a word for reading.
What it can reach
- private-dataThe name "get_contact_info" says "get" and "contact": it reads contacts.
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it TESSA's phone number, email, office address, business hours, and the links to book a call. Use this when someone wants to reach TESSA.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
get_pricingTESSA's current starting prices for every service, read live from https://tessa.tech/pricing/ (for example SEO, PPC, websites, AI avatars, accessibility).Reads text others writeNo findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it TESSA's current starting prices for every service, read live from https://tessa.tech/pricing/ (for example SEO, PPC, websites, AI avatars, accessibility). Use this when someone asks what TESSA charges or wants to compare prices. service: optional keyword to filter, for example 'seo' or 'website'
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
get_seo_offerTESSA's SEO offer in structured form: what it is, starting prices word for word from the pricing page (local, national and international SEO, Generative Engine Optimization), the s…No findings
Why it is in this group
- The name "get_seo_offer" says "get": a word for reading.
Description, as the server wrote it TESSA's SEO offer in structured form: what it is, starting prices word for word from the pricing page (local, national and international SEO, Generative Engine Optimization), the service page, and the link to book a free strategy session for the scope and an exact price. Scope, deliverables and timeline are included where TESSA has published them. Use this when someone asks about TESSA's SEO, local SEO, national SEO or Generative Engine Optimization (GEO).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_servicesList the services TESSA Marketing & Technology offers: SEO, paid ads, website design and development, AI chatbots and avatars, AI agent readiness, and web accessibility.No findings
Why it is in this group
- The name "get_services" says "get": a word for reading.
Description, as the server wrote it List the services TESSA Marketing & Technology offers: SEO, paid ads, website design and development, AI chatbots and avatars, AI agent readiness, and web accessibility. Use this when someone asks what TESSA does. For current prices call get_pricing. Optional filters: category_slug: marketing | web-development | ai-experiences | accessibility service_slug: one service, for example 'seo'
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_wcag_auditDetails of TESSA's WCAG 2.2 AA accessibility audit: scope, deliverables, timeline and price range.No findings
Why it is in this group
- The name "get_wcag_audit" says "get": a word for reading.
Description, as the server wrote it Details of TESSA's WCAG 2.2 AA accessibility audit: scope, deliverables, timeline and price range.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_web_ai_development_offerTESSA's website and AI development offer in structured form: what it is, starting prices word for word from the pricing page (website design, website development), the service page…Reads text others writeNo findings
Why it is in this group
- The name "get_web_ai_development_offer" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_web_ai_development_offer" says "get" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
Description, as the server wrote it TESSA's website and AI development offer in structured form: what it is, starting prices word for word from the pricing page (website design, website development), the service page, and the link to book a free strategy session for the scope and an exact price. Scope, deliverables and timeline are included where TESSA has published them. Use this when someone wants TESSA to design or build a website, a web application or AI software.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
45 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out5
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__tessa__get_contact_info"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:19 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://aiagent.tessa.tech/mcp: tools/list returned 14 tools to an anonymous client, including contact_tessa (irreversible), assess_ai_readiness (write), assess_seo (write), assess_ad_tracking (write), assess_website (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http tessa https://aiagent.tessa.tech/mcpclaude mcp add --transport http tessa https://aiagent.tessa.tech/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__tessa__get_services",
"mcp__tessa__get_pricing",
"mcp__tessa__get_contact_info",
"mcp__tessa__get_case_studies",
"mcp__tessa__get_seo_offer",
"mcp__tessa__get_advertising_offer",
"mcp__tessa__get_web_ai_development_offer",
"mcp__tessa__get_wcag_audit"
],
"ask": [
"mcp__tessa__assess_ai_readiness",
"mcp__tessa__assess_seo",
"mcp__tessa__assess_ad_tracking",
"mcp__tessa__assess_website",
"mcp__tessa__request_strategy_session",
"mcp__tessa__contact_tessa"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as tessa. Review it before you use it.
Capability tags behind 9 rules
- mcp__tessa__get_pricing untrusted-input
- mcp__tessa__get_contact_info private-data, untrusted-input
- mcp__tessa__get_web_ai_development_offer untrusted-input
- mcp__tessa__assess_ai_readiness untrusted-input, outbound
- mcp__tessa__assess_seo untrusted-input, outbound
- mcp__tessa__assess_ad_tracking untrusted-input, outbound
- mcp__tessa__assess_website untrusted-input, outbound
- mcp__tessa__request_strategy_session untrusted-input
- mcp__tessa__contact_tessa untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/tech.tessa/tessa-mcp-server/verify?hash=1c9cf8dcadb0b6488b2ef9c4744ae78577820f41ced83d81da680fc5f4b73c56" | jq -e '.changed == false'Pinned hash 1c9cf8dcadb0, from Nov 18, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/tech.tessa/tessa-mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/tech.tessa/tessa-mcp-server)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:55 UTC.
TESSA Marketing & Technology MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TESSA Marketing & Technology MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TESSA Marketing & Technology MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the TESSA Marketing & Technology MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: contact_tessa.
What tools does the TESSA Marketing & Technology MCP server have?
- 14 tools: 1 irreversible, 5 write, 8 read. contact_tessa, assess_ai_readiness, assess_seo, assess_ad_tracking, assess_website, request_strategy_session, get_services, get_pricing and 6 more.
Does the TESSA Marketing & Technology MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TESSA Marketing & Technology MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): assess_ai_readiness, assess_seo, assess_ad_tracking, assess_website and contact_tessa.
Has the TESSA Marketing & Technology MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.