Assurance
PYPI · ASSURANCE-MCP · SCANNED SEP 20
Checks what an agent did NOT read. Coverage over a retrieval step or a folder. No model.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 2 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 758 tokens (~151/item across 5 items; 5 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 Management50
- Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Assurance MCP server?
Assurance runs locally as a PyPI package, launched with uvx assurance-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · assurance-mcp
claude mcp add i-ops-hq-assurance-mcp -- uvx assurance-mcp
{
"mcpServers": {
"i-ops-hq-assurance-mcp": {
"command": "uvx",
"args": [
"assurance-mcp"
]
}
}
} {
"servers": {
"i-ops-hq-assurance-mcp": {
"command": "uvx",
"args": [
"assurance-mcp"
]
}
}
} codex mcp add i-ops-hq-assurance-mcp -- uvx assurance-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"i-ops-hq-assurance-mcp": {
"type": "local",
"command": [
"uvx",
"assurance-mcp"
],
"enabled": true
}
}
} openclaw mcp add i-ops-hq-assurance-mcp --command uvx --arg assurance-mcp
mcp_servers:
i-ops-hq-assurance-mcp:
command: "uvx"
args: ["assurance-mcp"] {
"McpServers": {
"i-ops-hq-assurance-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"assurance-mcp"
]
}
}
} assistant mcp add i-ops-hq-assurance-mcp -t stdio -c uvx -a assurance-mcp
{
"mcpServers": {
"i-ops-hq-assurance-mcp": {
"command": "uvx",
"args": [
"assurance-mcp"
]
}
}
} 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.
- 20 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.
- 19 Sept 26 0
- Stability: 0.43 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Package version: 0.4.7 → 0.4.8 functional
- 18 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.
- 16 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.
- 15 Sept 26 +1
- Security disclosure: fail → pass ▲ functional
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 11 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 0.4.6 → 0.4.7 functional
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 20 Sept 2026 · Analysed pypi/assurance-mcp@0.4.8
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 33 packages
| Packages resolved | 33 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
check_coverage_tool ~66
Check whether every month in a folder span is present. Read-only. Names a folder and optionally a period range such as 'January 2024 to December 2025' or 'last 12 months'.
| Name | Type | Req | Description |
|---|---|---|---|
| folder | string | yes | – |
| period_range | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
check_retrieval_coverage_tool ~304
Check a retrieval step: did something come back from every document the question spans? Read-only, touches no filesystem. Use this instead of `check_set_coverage_tool` whenever the thing you retrieved is CHUNKS, because the two sides are not the same unit. `retrieved_chunks` may be document ids, or the records your vector store returned — the parent document is read from `document`, `doc`, `source`, `path` or `id`, at the top level or under `metadata`. Chunks are reduced to parent documents and de-duplicated: five chunks of one document is one document covered, not five. **Do not diff chunk ids against a document scope.** Top-k returns k chunks and a scope holds more, so such a record can never be complete no matter how good the retrieval was. `expected_documents` is YOUR declaration — a metadata filter, a graph walk, a join. Never the retriever's own output: a denominator the retriever picks always reports that it did fine. Returns the coverage record. Documents retrieved from OUTSIDE the declared scope appear under `out_of_scope`; they earn no credit and do not make the run incomplete, but on a multi-tenant corpus they are often the more alarming line.
| Name | Type | Req | Description |
|---|---|---|---|
| derivation | – | – | – |
| expected_documents | array | yes | – |
| retrieved_chunks | array | yes | – |
| scope | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
check_set_coverage_tool ~263
Check what a task required against what was actually read, over any two sets of keys. Read-only, and touches no filesystem — the caller holds both lists. Use this when the thing you must account for is not dated files in a folder: documents the question spans against the chunks a retriever returned, files changed in a pull request against files reviewed, table partitions against partitions loaded, required controls against controls with evidence, declared eval cases against cases actually run. `expected` is the caller's declaration and is never inferred here. `scope` names the items for the sentence ("documents the question spans"); `where` names where they were looked for ("the retrieved set"); `derivation` records how the expected set was arrived at, so a reader can disagree with the denominator rather than only with the result. Returns the coverage record: `complete`, `read` of `required`, and each way an expectation failed to be evidence kept separate. Anything present that was not expected is reported under `unexpected` and deliberately earns no credit against the denominator.
| Name | Type | Req | Description |
|---|---|---|---|
| derivation | – | – | – |
| expected | array | yes | – |
| found | array | yes | – |
| scope | – | – | – |
| where | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
check_staleness_tool ~84
Check whether a document's figures still match a source file the caller names. Read-only. Does not search for a plausible match — both paths are required. Returns UNCHECKABLE when recorded facts are missing and cannot be read.
| Name | Type | Req | Description |
|---|---|---|---|
| document | string | yes | – |
| folder | string | yes | – |
| recorded_facts | – | – | – |
| source | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_dated_files_tool ~41
List which reporting periods a folder holds from dated filenames. Read-only. Helps an agent decide what to ask next.
| Name | Type | Req | Description |
|---|---|---|---|
| folder | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
What is the Assurance MCP server?
Assurance is an MCP server listed in the public MCP registry as io.github.i-ops-hq/assurance-mcp. Checks what an agent did NOT read. Coverage over a retrieval step or a folder. No model. This page covers its PyPI package (assurance-mcp).
Is the Assurance MCP server safe to use?
Assurance scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 Assurance MCP server expose?
Assurance exposes 5 tools: check_coverage_tool, check_staleness_tool, list_dated_files_tool, check_set_coverage_tool, check_retrieval_coverage_tool. Their descriptions and schemas cost roughly 758 tokens of context every time the server is loaded.
Is the Assurance MCP server still maintained?
Assurance is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Assurance MCP server under?
Assurance declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.