protogrid

Search / ai.agentlookups/overassessed

overassessed

R0· no sign-in

Maryland property-assessment fairness checks vs similar homes, with appeal windows and links.

v1.0.0 · active · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality77good
Trust77of 100
Uptime, 30 days100%
Latency p50214 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "overassessed": {
      "type": "http",
      "url": "https://overassessed.agentlookups.ai/mcp"
    }
  }
}
claude mcp add --transport http overassessed https://overassessed.agentlookups.ai/mcp
[mcp_servers.overassessed]
url = "https://overassessed.agentlookups.ai/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "overassessed": {
      "type": "remote",
      "url": "https://overassessed.agentlookups.ai/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "overassessed": {
      "type": "http",
      "url": "https://overassessed.agentlookups.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=overassessed&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vb3ZlcmFzc2Vzc2VkLmFnZW50bG9va3Vwcy5haS9tY3AifQ%3D%3D"
}
{
  "servers": {
    "overassessed": {
      "type": "http",
      "url": "https://overassessed.agentlookups.ai/mcp"
    }
  }
}
{
  "mcpServers": {
    "overassessed": {
      "httpUrl": "https://overassessed.agentlookups.ai/mcp"
    }
  }
}
extensions:
  "overassessed":
    enabled: true
    name: "overassessed"
    type: streamable_http
    uri: "https://overassessed.agentlookups.ai/mcp"
    timeout: 300

Quality 77 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene93 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • warn
    tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations1 of 1 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 909 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability50 · weight 15
  • pass
    stability.changes4 tool changes in 30 days
  • fail
    stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

1 tools, about 909 tokens to load them all · tool set 126fb04294ed · tools last changed 2026-09-29 · checked 2026-10-19 10:52 UTC

Tool changes

  • check_assessmentchangeddescription
    before

    Fairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales recent sales, and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. A zip is 5 digits; a ZIP+4 (21202-1234) is read as its first five digits. A malformed zip or acct returns an error field naming the expected form, a zip outside Maryland returns an error field stating that only Maryland is covered, and an acct the roll does not hold returns an error field stating that no parcel has that account id. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

    after · 86% of words in common

    Fairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales sales dated RatioFromYear through RatioToYear (three calendar years ending with the year of the roll's newest sale dated on or before today), and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. A single-match or multiple_matches result also carries a roll object: as_of is the date the state last updated the roll and pulled is the date this copy was taken (both YYYY-MM-DD), overdue is true when this copy is more than 35 days old, and a field the server does not know is left out. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. A zip is 5 digits; a ZIP+4 (21202-1234) is read as its first five digits. A malformed zip or acct returns an error field naming the expected form, a zip outside Maryland returns an error field stating that only Maryland is covered, and an acct the roll does not hold returns an error field stating that no parcel has that account id. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

  • check_assessmentchangeddescription, input schema
    before

    Fairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales recent sales, and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. An acct the roll does not hold returns the same error. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

    after · 93% of words in common

    Fairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales recent sales, and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. A zip is 5 digits; a ZIP+4 (21202-1234) is read as its first five digits. A malformed zip or acct returns an error field naming the expected form, a zip outside Maryland returns an error field stating that only Maryland is covered, and an acct the roll does not hold returns an error field stating that no parcel has that account id. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

  • check_assessmentchangedtitle, description, input schemameaning changed
    before

    Fairness check for a Maryland property assessment: where the address sits among genuinely similar homes (same reassessment group, similar size/lot/age, same zip), the group's median sales ratio, verdict branch (fair/review/elevated/insufficient), and Maryland's appeal windows with official filing links. If several parcels share the address, returns multiple_matches with account ids; re-call with acct.

    after · 25% of words in common

    Fairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales recent sales, and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. An acct the roll does not hold returns the same error. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

  • check_assessmentchangedannotations

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 77 / 100

no-repository
provenance45
liveness100
freshness85
hygiene80

+dns-namespace +reachable +uptime-100% ~updated-75d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://overassessed.agentlookups.ai/mcp streamable-httpnoneyes100%214 ms2025-06-182026-10-19

Tools (1)

check_assessmentread-onlyFairness check for one Maryland property assessment against genuinely similar homes (same triennial reassessment group, similar size, lot and age, same zip), from a copy of the state's own assessment roll (SDAT) refreshed monthly. Input is a street address plus zip, or an SDAT account id (acct). A single match returns the parcel record, a uniformity object, a plain-language verdict, Maryland's appeal windows with official filing links, and honesty notes. The uniformity object gives BandSize (how many similar homes), where the assessment sits among them as percentiles (PctFMV for market value, PctImprPSF for improvement value per square foot, PctLand for land value), their medians (MedianFMV, MedianImprPSF, MedianLand), the median sales ratio of assessment to sale price (MedianSalesRatio) and its coefficient of dispersion (COD) over RatioSales sales dated RatioFromYear through RatioToYear (three calendar years ending with the year of the roll's newest sale dated on or before today), and Branch. Verdict branches: fair means the assessment is in the normal range for similar homes; review means it is on the high side; elevated means it is higher than almost all of them; insufficient means fewer than 25 similar homes exist for a fair comparison, which is no finding either way. On the insufficient branch the percentile and median fields are 0, meaning not computed. A single-match or multiple_matches result also carries a roll object: as_of is the date the state last updated the roll and pulled is the date this copy was taken (both YYYY-MM-DD), overdue is true when this copy is more than 35 days old, and a field the server does not know is left out. MedianSalesRatio and COD are 0 when RatioSales is below 10, meaning no ratio is published. When several parcels share the address, the result is multiple_matches, listing parcels with their account ids; passing one of those ids as acct selects that parcel. When more than 10 parcels share an address (a condominium building, for instance), the list holds 10 of them, with no unit numbers and no total count, and a zip does not narrow it further; the official SDAT record has a record for every unit. When nothing matches, the result carries an error field; the roll writes addresses in its own form (e.g. 1 STATE CIR), so a miss can mean a different spelling, or a zip other than the one the roll records, rather than a missing parcel. A zip is 5 digits; a ZIP+4 (21202-1234) is read as its first five digits. A malformed zip or acct returns an error field naming the expected form, a zip outside Maryland returns an error field stating that only Maryland is covered, and an acct the roll does not hold returns an error field stating that no parcel has that account id. The check is a fairness snapshot of the public record, not an appraisal, and not legal advice; the official SDAT record is authoritative.

Schemas: list_tools.

Similar MCP servers

More from ai.agentlookups

Official server.json
{
  "name": "ai.agentlookups/overassessed",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json",
  "remotes": [
    {
      "url": "https://overassessed.agentlookups.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "description": "Maryland property-assessment fairness checks vs similar homes, with appeal windows and links."
}