MCP.Market

Assurance MCP server

by i-ops-hq·io.github.i-ops-hq/assurance-mcp·v0.5.10·7 stars

Checks what an agent did NOT read. Coverage over a retrieval step or a folder.

A91/100grade A
What users say
No reviews yet
Be the first
Safety scan
A91/100

not scanned yet

Adoption
Growing

7 stars230 downloads/wk

Reviews

Write one

Nobody has reviewed Assurance yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Assurance tools

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Assurance compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,461 AI and agents servers
GitHub stars
7
more than 81% of 2,713 AI and agents servers
Downloads a week
230
more than 76% of 1,554 AI and agents servers with a package

Release history: 12 versions in the registry since 2026-09-11, latest 2026-10-27, typically one every 4 days.

Install Assurance in Claude Code, Cursor or VS Code

claude mcp add assurance-mcp -- uvx assurance-mcp
Add to Cursor

What the publisher says

From the Assurance repository's README, as published. We do not edit it. Read it on GitHub

assurance

Software that reports success does not thereby prove it

Every tool here answers one question about work that has already happened, and refuses to answer it when it cannot. Nothing consults a model. Every result is arithmetic you can recompute yourself.

Start with the sentence that shows what that means in practice:

$ pip install assurance-budget
$ assurance-budget runs.jsonl

0 of 3 runs hit a limit — 1 was going nowhere first

  r-002
      Stopped: 3 rounds repeating fetch(url=api/invoices) and failing the same way
      (timeout) with nothing new read and no part of the goal closer. Continuing would
      spend the rest of this run's budget on the same result.

  Not tested by this log: iterations, retries, seconds. The log carries no events of
  that kind, so this is silence rather than a pass.

Read the last line again. The run passed three of the four limits — and the tool says so is not the same as says nothing. Most software reports the absence of a failure as a success, which is how a check that never ran becomes a green tick. This one names what it could not test, in the same breath as what it could.

That is the whole idea, and it is why these are separate from any product: a claim you can check is worth more than a claim you have to trust.

Three questions, three commands

Each installs on its own. None needs the others, an account, a service, or a network.

Did the work cover what it was supposed to cover?

pip install assurance-cli
assurance check ~/reports

No config and no corpus file — it reads the cadence, the span and what is absent from the filenames. A folder with no regular cadence is told so rather than handed a ratio.

Where did the run's budget go, and where did it go nowhere?

pip install assurance-budget
assurance-budget runs.jsonl --fail-on-exhausted

The expensive runs are rarely the ones that crash. They are the ones that retried the same failing call fourteen times and finished with a plausible answer and a bill. Ceilings are enforced by code the caller cannot talk out of them.

May this task proceed, for the person who asked?

pip install assurance-authority
assurance-authority team.json
1 of 3 tasks may proceed for the person who asked — 1 moved owner — 1 refused

  team roster      intern-42    proceed
  Q3 margin memo   intern-42    escalate_ownership -> CFO
      Priya (intern) may not receive finance-confidential, and CFO may. The task moves to
      CFO rather than the answer moving to Priya (intern).
  payroll extract  agent-a      refuse
      Drafting agent may not receive payroll, and nobody offered can. The task stops here.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Assurance: common questions

Is Assurance MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Assurance safety report
How do I install Assurance?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Assurance need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Assurance maintained?
The last commit was 23 days ago (2026-10-13). The latest release is v0.5.10.
What can I use instead of Assurance?
Servers from other publishers that do the same job: PDF MCP server, Tw Legal Rag MCP server and Serena MCP: the IDE for your agent MCP server.
How does Assurance compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,461 AI and agents servers); github stars 7 (more than 81% of 2,713 AI and agents servers); downloads a week 230 (more than 76% of 1,554 AI and agents servers with a package). Full comparison.

Alternatives to Assurance

Same job from other publishers: the closest match first, then the best rated.

  • PDF
    Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
    A
  • Tw Legal Rag
    Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations
    A
  • Serena MCP: the IDE for your agent
    A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
    C
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A