Fonteum — Healthcare Provider Data (Hosted)
Server Details
Hosted, zero-install MCP for source-provenanced US federal healthcare provider data. Resolve any NPI or CCN across NPPES, OIG LEIE, SAM.gov, state Medicaid exclusions, PECOS, Care Compare, and Open Payments — every field carries a 14-field provenance contract, with an "excluded or compromised anywhere" check on every lookup.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.6/5 across 7 of 7 tools scored.
Each tool has a unique purpose: exclusion checking, dataset metadata, historical records, source listing, verification, entity resolution, and search. No two tools overlap in functionality.
All tools start with 'fonteum_' and most follow a verb_noun pattern (e.g., check_exclusions, get_record). 'fonteum_dataset_info' is a minor deviation (noun_info instead of verb_noun), but overall naming is consistent and predictable.
With 7 tools, the set is well-scoped for providing healthcare provider data, exclusion checks, entity resolution, and historical records. No unnecessary tools, and the count is appropriate for the domain.
The tools cover key read-only operations: lookup, search, historical snapshots, exclusion checks, and verification. Minor gaps include no tool for batch queries or real-time monitoring, but core functionality is present.
Available Tools
7 toolsfonteum_check_exclusions_and_sanctionsAInspect
Check one name / NPI against US exclusion & debarment lists AND the global sanctions lists, each hit linked to its issuing authority and the date Fonteum captured it. By NPI: the unified compromised-anywhere screen — federal OIG LEIE, federal SAM.gov / GSA exclusions, state Medicaid exclusion lists, OIG Corporate Integrity Agreements, and CMS Civil Money Penalties. By name: the OFAC SDN + Consolidated, EU Consolidated Financial Sanctions, and UK / OFSI Consolidated sanctions lists. Exclusion & sanction-list monitoring for billing, program-integrity, and export-control compliance — aggregate dated facts only, no risk score, no label, no verdict. Re-confirm any match against the issuing authority. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| npi | No | 10-digit NPI to check against federal (OIG LEIE, SAM.gov) + state Medicaid exclusion lists, OIG CIA, and CMS penalties. Provide npi and/or name. | |
| name | No | Party name to screen against the OFAC SDN + Consolidated, EU, and UK sanctions lists (matches the listed primary name). Provide npi and/or name. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. Description explicitly states 'Read-only', clarifies it provides 'aggregate dated facts only, no risk score, no label, no verdict', and advises to 'Re-confirm any match against the issuing authority.' This fully discloses behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is moderately long but well-structured: starts with a one-sentence summary, then breaks into NPI and name sections, and ends with scope and advice. Each sentence adds value; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with two optional parameters and no output schema, the description adequately covers input semantics, behavioral traits, and the nature of results (linked hits with authority and date). Could be more explicit about the response structure, but acceptable given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds context by mapping 'npi' to specific federal/state lists and 'name' to sanctions lists, which is helpful beyond the schema's generic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description specifies verb 'Check' and resource 'one name / NPI against US exclusion & debarment lists AND the global sanctions lists', clearly differentiating between the two modes (by NPI for federal/state, by name for sanctions). Distinct from sibling tools (e.g., fonteum_recheck) which are for rechecking specific records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states the two use cases (by NPI or by name) and the compliance context (billing, program-integrity, export-control). Does not explicitly exclude other sibling tools, but the purpose is clear enough that an agent would know when to invoke this versus others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_dataset_infoAInspect
Return Fonteum dataset / source-family methodology + metadata: the methodology version, the canonical methodology URL, the fourteen-field provenance contract spec, and the full multi-vertical source catalog (85 government sources across healthcare, procurement, sanctions, and securities — live count). Read-only static data.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly states 'Read-only static data', clearly indicating no side effects. It details the output content (methodology version, URL, provenance contract, source catalog), which is sufficient behavioral disclosure for a simple read tool. No annotations to contradict or augment.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, efficient and to the point. Every phrase adds value, from the verb 'Return' to the list of items and the 'Read-only static data' qualifying statement.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description sufficiently explains the return values (methodology version, URL, provenance contract spec, source catalog). For a parameterless metadata tool, this is complete and clear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the schema coverage is trivially 100%. The description adds valuable context about the output, but no parameter description is needed. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns Fonteum dataset methodology and metadata, listing specific items like version, URL, provenance contract, and source catalog. It distinguishes itself from sibling tools which focus on records, exclusions, and searches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is a read-only, static data retrieval tool, suitable for initial understanding. No explicit when-not-to-use or alternatives are mentioned, but the context is clear and no misuse is likely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_get_record_as_ofAInspect
Return a federal contractor's record (SAM.gov registration + GSA/SAM exclusions + awards + FAPIIS + ownership) exactly as it stood on a captured date — pass uei or cage plus as_of=YYYY-MM-DD. This is the bitemporal differentiator: what the source published and Fonteum captured as of that date, for eligibility-at-award-date / FCA-defense questions, not today's value back-dated. Every block carries source + capture date + a fourteen-field provenance contract + a signed /verify link. Exact facts only — no risk score, no verdict. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| uei | No | 12-char GSA Unique Entity ID. Provide this OR `cage`. | |
| cage | No | 5-char CAGE / NCAGE code; resolved to the entity's UEI. Provide this OR `uei`. | |
| as_of | Yes | Captured date as YYYY-MM-DD. The entity's registration + exclusion state is reproduced exactly as it stood on that date (bitemporal). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It explicitly states 'Read-only' and describes the return structure in detail: 'Every block carries source + capture date + a fourteen-field provenance contract + a signed /verify link'. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph but packs necessary information without waste. Minor improvement could be made with bullet points or breaking into sub-sections, but it remains efficient and front-loaded with key points.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the return value and provenance. It covers purpose, usage, parameters, and behavioral aspects comprehensively for a tool with three parameters and no nested objects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all three parameters. The description adds significant value by explaining the relationship between uei and cage (alternatives), the format of as_of, and the bitemporal interpretation, going beyond the schema's property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns a federal contractor's record as of a captured date, specifying the bitemporal nature. It distinguishes from siblings by emphasizing 'exact facts only — no risk score, no verdict' and 'Read-only', differentiating it from other tools that might provide risk assessments or current data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use scenarios: 'for eligibility-at-award-date / FCA-defense questions' and clarifies it is not for today's value back-dated. While it does not name specific sibling alternatives, the context is clear enough for an agent to understand appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_list_sourcesAInspect
List every government source Fonteum ingests across all verticals — US healthcare (NPPES, CMS, OIG, HRSA), federal procurement (SAM.gov, USASpending), global sanctions (OFAC SDN, EU, UK), and corporate/securities registries (SEC) — each with its issuing authority, vertical, re-capture cadence, and official source URL. 85 sources total (live count). Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses the tool's readonly nature and provides additional behavioral context: it returns a live count of 85 sources, each with specific attributes (issuing authority, vertical, cadence, URL). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose. While the list of verticals is informative, it makes the description slightly longer than necessary, but still efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and no output schema, the description provides complete context: the output is a list of sources with detailed attributes (authority, vertical, cadence, URL) and a live count of 85. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so schema coverage is 100%. The description adds no parameter-specific info, but this is appropriate since no parameters exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('every government source Fonteum ingests'), clearly stating the scope across verticals. It distinguishes from siblings like search_records by being a straightforward enumeration tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly indicates this is a read-only listing tool, implying use when needing inventory of sources. It lacks explicit when-not or alternative references, but the context is sufficiently clear given the sibling tools are for different purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_recheckAInspect
Return the signed fingerprint + live source link to independently re-check a Fonteum fact — the 'don't trust our data, re-check it' loop. Without a snapshot id: the live Ed25519 attestation-chain head plus the public re-check endpoints (/verify, POST /api/v1/chain/verify, the public key). With a snapshot id: that snapshot's signed content hash, the upstream source archive URL, and the /verify/{id} deep link, so you can download the source and recompute the hash. Signatures attest fidelity-to-source (matches what the source published on the captured date), never truth. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| snapshot_id | No | Optional snapshot id (from a record's attestation). When given, returns that snapshot's signed content hash + the live source archive URL + the deep /verify/{id} link. Omit for the live attestation-chain head. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses read-only nature, signature purpose (fidelity, not truth), and details of each case. Transparent and comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with a summary sentence followed by detailed cases. Every sentence adds value, no fluff, appropriate length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description explains what is returned in each case, including verification endpoints. Complete for a one-parameter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds significant value by explaining the behavior with and without snapshot_id, and what the snapshot_id is used for, beyond the schema's minimal description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns signed fingerprint and live source link for re-checking facts, with two distinct modes (with/without snapshot_id). It distinguishes itself from sibling tools like fonteum_check_exclusions_and_sanctions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use each mode (with/without snapshot_id) and implies when not to use (e.g., for exclusions, use sibling). Lacks explicit 'when not to use' statement but is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_resolve_entityAInspect
Resolve the canonical entity for an identifier and ground every fact in its government source. NPI (10-digit) returns the US healthcare provider's NPPES record plus the unified exclusion / program-integrity screen (OIG LEIE + SAM.gov + state Medicaid + OIG CIA + CMS penalties). UEI (12-char GSA Unique Entity ID) or CAGE returns the federal contractor's SAM.gov registration, GSA/SAM exclusions, USASpending awards, FAPIIS records, and FAR 4.18 ownership. Every block carries source + capture date + a fourteen-field provenance contract + a signed, re-checkable /verify link. Exact facts only — no risk score, no label, no verdict. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The entity identifier: a 10-digit NPI (healthcare provider), a 12-char GSA UEI, or a 5-char CAGE code (federal contractor). | |
| id_type | No | Identifier scheme. Omit to auto-detect from the id format. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses read-only nature, exact facts only (no risk scores/labels), provenance with capture date and verify links. No annotations were provided, so the description fully covers behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is informative but not overly verbose. It is structured with a clear first sentence, followed by detailed breakdowns per identifier type, and ends with notes on provenance and read-only. Slightly long but every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two parameters and no output schema, the description provides sufficient context: what identifiers are accepted, what data is returned (including provenance), and that it is read-only. No gaps for an entity resolution tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%. The description adds meaning by explaining the id_type parameter is optional with auto-detection, and provides examples of valid identifier formats for each type.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool resolves canonical entities for identifiers and grounds facts in government sources. It differentiates from siblings by detailing specific data returned for NPI and UEI/CAGE, which is distinct from check_exclusions_and_sanctions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (when needing entity resolution with grounded facts). It explains supported identifier formats and that id_type is optional, but does not explicitly state when not to use it or compare to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fonteum_search_recordsAInspect
Search records by attribute across Fonteum's graph. Returns matching US healthcare providers by vertical + state from the public CMS NPPES NPI Registry (up to 100 per call), each with source + capture date + a fourteen-field provenance contract and a signed /verify link. For identifier-keyed lookups (NPI, UEI/CAGE, sanctioned-party name) use fonteum_resolve_entity or fonteum_check_exclusions_and_sanctions. Healthcare verticals: chiropractors, dermatologists, plastic-surgeons, med-spas, weight-loss, rehab-centers, hair-transplant, fertility-clinics, trt-clinics, ketamine-clinics. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max records to return (default 25, max 100). | |
| state | Yes | 2-letter USPS state code (e.g. 'CA', 'TX'). | |
| county | No | Optional county filter (preserved on the result; NPPES does not publish county-of-practice). | |
| vertical | Yes | Healthcare vertical slug. One of: chiropractors, dermatologists, plastic-surgeons, med-spas, weight-loss, rehab-centers, hair-transplant, fertility-clinics, trt-clinics, ketamine-clinics. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses read-only nature, a max of 100 results per call, and details about the return structure (source, capture date, provenance contract, verify link). Missing explicit mention of pagination or error handling, but adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at 4-5 sentences, front-loaded with purpose, and well-structured. No wasted words, but could be slightly more streamlined.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters, no output schema, and no annotations, the description provides sufficient context: purpose, usage boundaries, and result structure. Lacks details on error responses or rate limits, but overall complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with all parameters having descriptions. The description adds minimal extra meaning beyond what the schema provides; it repeats the vertical list and state format. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches records by attribute across Fonteum's graph, specifying it returns US healthcare providers by vertical and state from the CMS NPPES NPI Registry. It distinguishes itself from siblings by noting that identifier-keyed lookups should use other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when not to use this tool ('For identifier-keyed lookups... use fonteum_resolve_entity or fonteum_check_exclusions_and_sanctions'), providing clear alternatives. It also lists the allowed verticals.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!