cvd-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cvd-mcpCheck if the pricing context for Q3 is still fresh."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Reference implementation of the Context Validity Declaration (CVD) from the position paper The Agent Steward: Context Provenance and Temporal Validity as a Missing Governance Dimension in Multi-Agent Enterprise Ecosystems (Kefreen Lacerda, 2026).
The silent failure
An agent serving organizational context — prices, policies, product facts — that has silently gone out of date passes every technical health check. It responds within SLA. It returns success. It raises no exception. It is simply wrong.
A stale spreadsheet at least shows an old timestamp. A stale agent answer carries no observable signal at all:
{
"sku": "WIDGET-PRO",
"unit_price_usd": 4800.00
}Price list changed 9 days ago. The agent doesn't know. Neither do you. Confidently wrong — and invisible.
{
"status": "refused",
"reason": "context_expired",
"disclosure": "…last validated 14 days
ago… The accountable steward is
Ana Souza; contact them to revalidate."
}Visibly stale — and recoverable. Someone accountable is one message away.
The CVD attaches a small, declarative validity contract to any exposed context (an MCP tool/resource, or an Agent Card) so that obsolescence becomes detectable at runtime.
Related MCP server: agent-gate
How it works
flowchart LR
A["agent calls<br/>guarded tool"] --> B{"age =<br/>now − last_validated"}
B -->|"age ≤ freshness_slo"| C["✅ FRESH<br/>answer, unchanged"]
B -->|"age > freshness_slo"| D{"decay_policy<br/>.on_violation"}
D -->|refuse_with_disclosure| E["🛑 refusal that<br/>names the steward"]
D -->|warn| F["⚠️ answers,<br/>but flagged"]
D -->|escalate_to_steward| G["📣 routed to<br/>escalation target"]
D -->|"unknown policy"| EOne decision point, four outcomes — and the unsafe path (answering on expired context as if nothing happened) does not exist.
The five primitives
A CVD manifest declares exactly five fields. Nothing more:
# | Primitive | Meaning |
1 |
| Named identity of the accountable human — a person, not a functional mailbox |
2 |
| The system this context derives from |
3 |
| Maximum tolerated staleness, as an ISO 8601 duration ( |
4 |
| ISO 8601 timestamp of the last affirmative human validation |
5 |
|
|
As a manifest (examples/pricing_context.json):
{
"steward": "Ana Souza (Head of Pricing Operations)",
"source_of_record": "SAP ERP price list PL-2026-Q3",
"freshness_slo": "P7D",
"last_validated": "2026-07-15T09:00:00Z",
"decay_policy": {
"on_violation": "refuse_with_disclosure",
"fallback": "escalate_to_steward"
}
}freshness_slo rejects years and months (P1Y, P1M) — they don't map to a fixed duration. Express the window in days: P30D, P365D. Timestamps accept a trailing Z; naive timestamps are treated as UTC.
Install
pip install -e . # core — zero dependencies, Python ≥ 3.9
pip install -e ".[mcp]" # + official MCP Python SDK, for the example server
pip install -e ".[dev]" # + pytestThe core (cvd.models, cvd.evaluator, cvd.guard) is standard library only. It installs, imports, and tests without mcp — the SDK is needed only for the example server.
Quickstart
Two lines of ceremony: declare the contract, guard the function.
from cvd import ContextValidity, DecayPolicy, cvd_guard
pricing_cv = ContextValidity(
steward="Ana Souza (Head of Pricing Operations)",
source_of_record="SAP ERP price list PL-2026-Q3",
freshness_slo="P7D",
last_validated="2026-07-15T09:00:00Z",
decay_policy=DecayPolicy(on_violation="refuse_with_disclosure"),
)
@cvd_guard(pricing_cv)
def get_enterprise_price(sku: str) -> dict:
return {"sku": sku, "unit_price_usd": 4800.00}While the context is fresh, the function behaves as if the guard weren't there. Once it expires, the function is not even called — the caller gets the structured refusal instead.
Need the decision itself, or prefer exceptions?
from cvd import evaluate, ContextExpired
decision = evaluate(pricing_cv) # Decision(freshness, allowed, action, age, slo, …)
@cvd_guard(pricing_cv, raise_on_expired=True)
def get_price(sku: str) -> dict: ... # raises ContextExpired, carrying the Decision
| Wrapped call | Result when stale |
| not invoked |
|
| invoked |
|
| not invoked | refusal + |
anything unknown | not invoked | fails safe as |
Guarding an MCP tool
The guard stacks directly under @mcp.tool() — functools.wraps keeps the signature intact for the SDK's introspection (src/cvd/mcp_server.py):
from mcp.server.fastmcp import FastMCP
from cvd import cvd_guard
mcp = FastMCP("pricing-context-server")
@mcp.tool()
@cvd_guard(PRICING_CV)
def get_enterprise_price(sku: str) -> dict:
...pip install -e ".[mcp]"
python -m cvd.mcp_serverThe bundled manifest is deliberately past its window, so the tool refuses out of the box. Update last_validated to a recent timestamp and it answers normally.
See it fail loud
python demo.py — deterministic, no third-party packages. It evaluates the same manifest at two explicit instants:
=== 2. STALE — past the 7-day window (age: 14 days) ===
freshness : STALE
allowed : False
action : refuse
tool result : {
"status": "refused",
"reason": "context_expired",
"disclosure": "This context derives from SAP ERP price list PL-2026-Q3 and has
exceeded its freshness SLO of P7D: it was last validated 14 days ago, on
2026-07-15T09:00:00Z. The accountable steward is Ana Souza (Head of Pricing
Operations); contact them to revalidate."
}CVD demo — fail loud, not fail confident
manifest: examples/pricing_context.json
=== 1. FRESH — within the 7-day window (age: 2 days) ===
now : 2026-07-17T09:00:00+00:00
last_validated : 2026-07-15T09:00:00Z
freshness_slo : P7D
freshness : FRESH
allowed : True
action : answer
tool result : {
"sku": "WIDGET-PRO",
"unit_price_usd": 4800.0,
"currency": "USD"
}
=== 2. STALE — past the 7-day window (age: 14 days) ===
now : 2026-07-29T09:00:00+00:00
last_validated : 2026-07-15T09:00:00Z
freshness_slo : P7D
freshness : STALE
allowed : False
action : refuse
tool result : {
"status": "refused",
"reason": "context_expired",
"disclosure": "This context derives from SAP ERP price list PL-2026-Q3 and has exceeded its freshness SLO of P7D: it was last validated 14 days ago, on 2026-07-15T09:00:00Z. The accountable steward is Ana Souza (Head of Pricing Operations); contact them to revalidate.",
"escalate_to": null
}Run the tests with pytest — 34 cases covering the freshness boundary, all four decay policies, both parsers, and the guard's no-call guarantee.
Why refuse instead of answer?
Because a visible refusal is a recoverable operational event; a confident wrong answer is an invisible one.
An agent whose context has exceeded its freshness window must refuse to answer with confidence — returning a disclosure that names the accountable steward — rather than answer incorrectly with confidence. The refusal is not a failure of the system. It is the system working: obsolescence, which used to be silent, now produces a signal, an owner, and a path back to validity.
age == slocounts as FRESH. The SLO is a tolerance, not a fuse; the boundary belongs to the caller.Unknown policies fail safe. A typo in
decay_policymust never silently become "answer anyway".The steward is a person. Disclosure that names
pricing-team@names no one. Accountability needs a face.Years/months rejected in SLOs.
P1Mis 28–31 days depending on when you ask — an ambiguous freshness window is a contradiction in terms.The clock is injectable (
evaluate(cv, now=…),cvd_guard(cv, now_fn=…)), so every behavior in this README is reproducible in a test.
Citation
Lacerda, K. (2026). The Agent Steward: Context Provenance and Temporal Validity
as a Missing Governance Dimension in Multi-Agent Enterprise Ecosystems.
Zenodo. https://doi.org/10.5281/zenodo.21660205This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceAn MCP server that provides fact-checking capabilities and truth anchoring for AI agents using verified data sources.Last updatedMIT
- AlicenseBqualityAmaintenanceAn MCP server that enforces fail-closed deterministic checks, independent refute-first review, and tamper-evident hash-chained receipts for AI agent outputs before claiming completion.Last updated43MIT
- Alicense-qualityCmaintenanceMCP server providing agent memory with deterministic deletion guarantees, enabling compliant event storage, context retrieval, and audit-proof data management.Last updatedApache 2.0
- Alicense-qualityBmaintenanceAn MCP server that enforces explicit task ownership acceptance and requires a provenance tag (observed, reviewed, or reported) on every completion claim, preventing silent inheritance and unverified assertions in multi-agent systems.Last updated10,1711MIT
Related MCP Connectors
A paid remote MCP for agent memory MCP, built to return verdicts, receipts, usage logs, and audit-re
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kefreen/cvd-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server