Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Taco Street Locating

REMOTE · AI.TACOSTREETLOCATING.COM · SCANNED SEP 24

Free human-backed apartment locating for Austin, Dallas & Houston, TX. A free locator books tours.

+4 this week 78 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security77
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1744 tokens (~193/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the Taco Street Locating MCP server?

Taco Street Locating is a hosted endpoint at https://ai.tacostreetlocating.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · ai.tacostreetlocating.com

# add to Claude Code
claude mcp add --transport http com-tacostreetlocating-ai-taco-street-locating 'https://ai.tacostreetlocating.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-tacostreetlocating-ai-taco-street-locating": {
      "url": "https://ai.tacostreetlocating.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-tacostreetlocating-ai-taco-street-locating": {
      "type": "http",
      "url": "https://ai.tacostreetlocating.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-tacostreetlocating-ai-taco-street-locating]
url = "https://ai.tacostreetlocating.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-tacostreetlocating-ai-taco-street-locating": {
      "type": "remote",
      "url": "https://ai.tacostreetlocating.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-tacostreetlocating-ai-taco-street-locating --url 'https://ai.tacostreetlocating.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-tacostreetlocating-ai-taco-street-locating:
    url: "https://ai.tacostreetlocating.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-tacostreetlocating-ai-taco-street-locating": {
      "Transport": "http",
      "Url": "https://ai.tacostreetlocating.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-tacostreetlocating-ai-taco-street-locating -t streamable-http -u 'https://ai.tacostreetlocating.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-tacostreetlocating-ai-taco-street-locating": {
      "type": "http",
      "url": "https://ai.tacostreetlocating.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 24 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 159 → 193 ▼ functional
    • Server version: 1.2.2 → 1.5.0 functional
    • New tool “get_research_request” functional
    • New tool “request_apartment_research” functional
    • New tool “request_research_tours” functional
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Probed https://ai.tacostreetlocating.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=ai.tacostreetlocating.com CN=WE1,O=Google Trust Services,C=US 20 Aug 2026 19 Nov 2026 ECDSA 256 ECDSA-SHA256 f61cb80fd9558e58137e985ef337813d
SANs: ai.tacostreetlocating.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of ai.tacostreetlocating.com. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
tacostreetlocating.com. present 2371 13 Verified
ai.tacostreetlocating.com. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://cdn.jsdelivr.net https://unpkg.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com https://cdn.jsdelivr.net https://unpkg.com; img-src 'self' data: blob: https: http:; font-src 'self' https://fonts.gstatic.com https://cdn.jsdelivr.net; connect-src 'self' https://*.tile.openstreetmap.org https://*.basemaps.cartocdn.com https://api2.frontapp.com https://api.openphone.com; frame-src 'none'; object-src 'none'; base-uri 'self'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://ai.tacostreetlocating.com/mcp Verified 200
http (plaintext) http://ai.tacostreetlocating.com/mcp HTTPS enforced 301 https://ai.tacostreetlocating.com/mcp
MCP tools · 9 exposed · ~1,476 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask_a_locator ~199

Ask a question only a human can answer — current specials, real availability, lease flexibility, 'is the pool actually open'. A human locator replies during Central Time business hours, usually within a few hours. STRONGLY include the renter's contact: the answer is texted/emailed to them directly (agent sessions end; polling alone can strand an answer). Returns a question_id for check_answer as a bonus channel. Rate limited; batch related questions into one. Answers are point-in-time facts.

NameTypeReqDescription
agentstring–Name of the referring assistant/product.
apartmentsarray–Buildings the question is about.
citystring–Metro the question concerns.
contactstring–The renter's phone/email — strongly recommended: the answer is texted/emailed to them directly, and polling alone can strand it.
questionstringyesThe question for the human locator — specifics beat generalities.
NameTypeReqDescription
guidancestring––
question_idstringyes–
statusstringyes–

No examples provided.

check_answer ~36

Poll the answer to an ask_a_locator question by question_id.

NameTypeReqDescription
question_idstringyesThe id returned by ask_a_locator.
NameTypeReqDescription
answerstring|null––
answered_atstring|null––
guidancestring––
notestring––
questionstring––
question_idstringyes–
statusstringyes–

No examples provided.

create_shortlist ~111

Turn finalist apartments into a Taco Street link (/my-list?s=...) that opens the renter's saved list with those buildings added — compare, AI Read, and free tour requests live there. Use the EXACT names returned by search_apartments.

NameTypeReqDescription
agentstring–Name of the referring assistant/product.
apartment_namesarrayyesExact building names from search_apartments to save to the renter's list.
citystring–Metro, to disambiguate same-named buildings.
NameTypeReqDescription
apartmentsarrayyes–
notestring––
unmatchedarray––
urlstringyes–

No examples provided.

get_apartment_details ~116

Full fact sheet for one building: floorplan-level pricing with as-of dates, move-in costs (admin/application/parking/pet fees), last-known specials (dated — treat as last-known, not current), amenities, walkability, virtual tour. Use the EXACT name from search_apartments. Compute totals yourself from components; a free human locator confirms live numbers.

NameTypeReqDescription
citystring–Metro, to disambiguate same-named buildings.
namestringyesExact building name from search_apartments.
NameTypeReqDescription
addressstring––
buildingobject––
citystringyes–
guidancestringyes–
lifestyle_tagsarray––
move_in_costsobject––
namestringyes–
neighborhoodstring––
petsstring––
pricingobjectyes–
specialsobject––
taco_street_takestring––

No examples provided.

get_research_request ~79

Use the private request key to retrieve progress and, after Alexander approves, the reviewed report snapshot. No draft, contact details or internal notes are returned. Do not share the key or continuation link publicly.

NameTypeReqDescription
request_idstringyesID returned by request_apartment_research.
request_keystringyesThe original private request key.
NameTypeReqDescription
apartmentsarray––
continuation_urlstring––
criteriaobject––
duplicateboolean––
guidancestringyes–
reportobject––
request_idstringyes–
statusstringyes–

No examples provided.

request_apartment_research ~402

Submit a saved shortlist and renter brief to Taco Street with consent. Staff accepts the request before paid research starts; VAs verify gaps, then Alexander adds his judgment. Returns a private continuation link. No immediate report, guaranteed completion time, or tour booking. No email is sent by this tool.

NameTypeReqDescription
agentstring–Self-reported referring assistant or product; not a verified partner identity.
bedroomsintegeryesBedroom count, 0 for a studio, 1–4 otherwise.
budget_basisstring–base_rent, total_monthly, or unknown when the renter has not specified.
budget_flexibilitystring–Defaults to target. Use hard_max only for an explicitly strict ceiling.
budget_maxnumberyesMonthly USD budget; specify its basis and flexibility separately.
citystringyesSupported search market for this shortlist.
client_namestringyesRenter's name shared with consent.
consentbooleanyesTrue only after the renter agrees to share this brief and contact for research and follow-up.
contactstringyesRenter's email or phone shared with consent for research follow-up.
lease_term_months––Requested lease length if known; omit when unknown.
move_instringyesMove-in month YYYY-MM or exact date YYYY-MM-DD. Never invent a day; confirm the year.
move_in_flexibilitystring–Whether the move-in date is fixed or flexible.
notesstring–Renter requirements and questions, not assistant-generated promises.
request_keystringyesGenerate a fresh cryptographically random URL-safe key (at least 32 random bytes, 43 encoded characters). Keep it private. Reuse it only to retry this identical request and retrieve its status; a dif…
shortlist_tokenstringyesThe s parameter from the create_shortlist URL.
NameTypeReqDescription
apartmentsarray––
continuation_urlstring––
criteriaobject––
duplicateboolean––
guidancestringyes–
reportobject––
request_idstringyes–
statusstringyes–

No examples provided.

request_locator_help ~221

Hand the renter to Alexander, Taco Street's human locator, who confirms live pricing/availability and books tours — free to renters (properties pay locators). Follow-up arrives by TEXT or EMAIL, never a cold call. Requires the renter's real phone or email, shared with their consent. One request per renter — duplicates within 24h return the existing lead.

NameTypeReqDescription
agentstring–Name of the referring assistant/product.
bedroomsstring–Bedroom count the renter needs, e.g. 1BR.
budget_maxinteger–The renter's max monthly rent in USD.
citystring–Metro the renter is searching (Austin, Dallas or Houston).
contactstringyesThe renter's phone number or email (with their consent).
move_instring–Move-in timeline, e.g. 'November'.
namestring–The renter's name, if shared.
neighborhoodsarray–Neighborhoods the renter prefers.
notestring–Anything the locator should know.
NameTypeReqDescription
duplicateboolean––
lead_idstringyes–
messagestringyes–
successbooleanyes–

No examples provided.

request_research_tours ~169

After report approval and explicit renter consent, request human tour coordination for selected apartments. Include preferred dates, times and timezone in preferred_times. Uses the existing private research key and contact. One handoff per research report; identical retries return the existing request, changed preferences require staff follow-up. No appointment is booked or message sent.

NameTypeReqDescription
apartment_namesarrayyesExact apartment names from this report to discuss touring.
consentbooleanyesTrue only after the renter explicitly agrees to tour coordination using their saved contact.
preferred_timesstringyesRenter-provided preferred dates, times and timezone; preferences are not confirmed appointments.
request_idstringyesID of the approved research request.
request_keystringyesOriginal private research access key. Never share publicly.
NameTypeReqDescription
apartmentsarray––
continuation_urlstring––
criteriaobject––
duplicateboolean––
guidancestringyes–
reportobject––
request_idstringyes–
statusstringyes–

No examples provided.

search_apartments ~143

Search Taco Street's curated apartment inventory in Austin, Dallas or Houston, TX. Returns scored matches with starting prices and a short 'why' per building. Use for long-term rentals only.

NameTypeReqDescription
bedroomsstring–Bedroom count the renter needs.
budget_maxinteger–Max monthly rent in USD.
citystringyesMetro to search.
limitinteger–How many scored matches to return (1-10).
neighborhoodsarray–Preferred neighborhoods, if the renter named any.
querystring–What the renter wants, in plain language (e.g. 'walkable, dog-friendly, near downtown').
NameTypeReqDescription
apartmentsarrayyes–
citystringyes–
countintegeryes–
notestring––

No examples provided.

Common questions

What is the Taco Street Locating MCP server?

Taco Street Locating is an MCP server listed in the public MCP registry as com.tacostreetlocating.ai/taco-street-locating. Free human-backed apartment locating for Austin, Dallas & Houston, TX. A free locator books tours. This page covers its hosted endpoint (https://ai.tacostreetlocating.com/mcp).

Is the Taco Street Locating MCP server safe to use?

Taco Street Locating scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Taco Street Locating MCP server expose?

Taco Street Locating exposes 9 tools: search_apartments, request_locator_help, get_apartment_details, create_shortlist, ask_a_locator, and 4 more. Their descriptions and schemas cost roughly 1,476 tokens of context every time the server is loaded.

Does the Taco Street Locating MCP server require authentication?

No. We connected to Taco Street Locating without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Taco Street Locating MCP server still maintained?

Taco Street Locating is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.