Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Physical Capability Cloud

REMOTE · CAPABILITY.NETWORK

Discover, hire, and verify real-world physical capability through MCP.

0 this week 79 Trust /100

Last scanned (10 hours ago)

Scores higher than 79% of remote servers

Reachable. Last reached 5 Nov 2026.

Category IoT and Hardware

Recent critical change

Authorization (1 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 22909 tokens (~88/item across 260 items; 256 tools + 4 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 92% of tool parameters carry a description.Partial
  • Structured output schemas are declared (3% of tools); any adoption earns full credit.Pass
Tool Safety97
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 13 of 15 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_transfer_graphs" implies "transfer" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 258 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 5 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 3 Nov 26 0
    • Stability: fail → pass ▲ security
  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 96 to 99.

  • 29 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 89 to 93.

  • 27 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 86.

  • 25 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 76 to 79.

  • 23 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 69 to 73.

  • 20 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 59 to 63.

Diagnostics

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 5 Nov 2026 · Probed https://capability.network/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=capability.network CN=YE1,O=Let's Encrypt,C=US 14 Sept 2026 13 Dec 2026 ECDSA 256 ECDSA-SHA384 61e79ee07e783aedc9770a1b1a54789ebd0
SANs: *.capability.network, capability.network
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of capability.network. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
network. DS published 11416, 40414 8, 8 Verified
capability.network. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://capability.network/mcp Verified 200
http (plaintext) http://capability.network/mcp HTTPS enforced 301 https://capability.network/mcp
MCP tools · 256 exposed · ~22,670 tokens

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 →

Tool Tokens
pcc.op.capability.request_quote ~96

Price a configured PCC capability (typed operation). Returns the itemized quote for the given capability type + selections. Pure calculation — no funds move and nothing is created. Maps to POST /api/build/price.

NameTypeReqDescription
capabilityIdstring––
profileIdstring––
selectionsobjectyesParameter selections.
typestringyesCapability type, e.g. 'fdm'.

No output schema declared.

No examples provided.

propose_composition ~281

Propose a composition — a sequenced DAG of capability instances to satisfy a multi-step outcome under a budget + assurance tier. Accepts either a flat `steps` list or an outcome chain. Returns a candidate plan ranked by `optimizeFor` (price | speed | quality) with per-step assignments. The composition is persisted for ~30 minutes (proposed status) and can be executed once via execute_composition.

NameTypeReqDescription
budgetUSDnumberyesTotal budget the user is willing to spend across all steps.
descriptionstring–Free-form natural-language description (≤4000 chars).
locationobject–Geographic constraint (lat/lng + radius, or country, etc).
minAssuranceTierintegeryesMinimum acceptable assurance tier on every step.
optimizeForstring–Ranking objective (default `price`).
outcomeChainarray–Alternative to `steps`: chain of named sub-outcomes. The planner expands each into capability types.
outcomeTypestringyesHigh-level outcome label, ≤120 chars. Example: 'desk-robot-prototype'.
requesterobject–{agentId, did?} — the agent submitting the request.
stepsarray–Ordered list of capability types this composition needs (1..20). Use this OR `outcomeChain`.

No output schema declared.

No examples provided.

protocol_create_escrow ~129

Create a new MilestoneEscrow contract via the PCCProtocol factory on-chain. Protocol-deployed escrows have fee collection and registry tracking built in. Requires PCC_GATEWAY_PRIVATE_KEY write access.

NameTypeReqDescription
arbiterstringyesArbiter EVM address (0x...) — resolves disputes
cwmIdstringyesCapability Work Module ID as a 32-byte hex string (0x + 64 chars)
payerstringyesPayer EVM address (0x...)
tokenstringyesERC-20 token address for payment (0x...)

No output schema declared.

No examples provided.

protocol_escrow_fees ~55

Get protocol fees collected from a specific escrow contract. Also returns whether the escrow was deployed via the protocol factory. Useful for auditing fee flows.

NameTypeReqDescription
escrowAddressstringyesEscrow contract address (0x...)

No output schema declared.

No examples provided.

protocol_fee ~89

Calculate the protocol fee for a given USDC amount (6-decimal units). Returns the fee, the net amount after fee, and formatted versions of both. Use this before building escrow contracts to understand the true cost.

NameTypeReqDescription
amountstringyesAmount as a BigInt string in USDC 6-decimal units (e.g. '1000000000' = 1000 USDC)

No output schema declared.

No examples provided.

protocol_state ~44

Read the PCCProtocol root contract state: current fee rate, total protocol fees collected, total escrow count, and registry addresses. Requires PCC_PROTOCOL_ADDRESS to be configured on the gateway.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

protocol_token_fees ~55

Get total protocol fees collected for a specific ERC-20 token address across all escrows. Returns raw wei amount and human-readable formatted value.

NameTypeReqDescription
tokenAddressstringyesERC-20 token contract address (0x...)

No output schema declared.

No examples provided.

prove_registration ~105

Fast-track: submit evidence that your device works and get auto-approved + activated immediately. No manual review needed. Submit a photo of test output, device health snapshot, or a full evidence bundle with completion events. If evidence meets requirements, registration jumps straight to 'active'.

NameTypeReqDescription
evidenceobjectyesEvidence proving the device works. Include at least one of: bundleHash+events, photoBase64, or deviceHealth.
registrationIdstringyesRegistration ID to prove

No output schema declared.

No examples provided.

provision_api_key ~151

CALL THIS FIRST. Provisions an API key for the operator. Returns a pcc_live_* key that must be included as 'Authorization: Bearer <key>' on all subsequent requests. Accepts either email OR walletAddress. The key is shown once — save it. Without it, all other endpoints return 401.

NameTypeReqDescription
capabilitystring–What the operator does — e.g. 'FDM 3D printing', 'CNC milling', 'HPLC analysis'
emailstring–Operator email address (use this OR walletAddress)
namestring–Operator display name (optional)
walletAddressstring–EVM wallet address (use this OR email)

No output schema declared.

No examples provided.

publish_protocol ~40

Publish a draft protocol template, making it visible in the protocol library for others to discover and use.

NameTypeReqDescription
idstringyesProtocol template ID to publish

No output schema declared.

No examples provided.

raise_ip_dispute ~63

Raise a Story Protocol IP dispute against an asset. Provide evidence hash and reason.

NameTypeReqDescription
evidenceHashstringyesHash of the dispute evidence
ipIdstringyesIP asset ID to dispute
reasonstringyesReason for the dispute

No output schema declared.

No examples provided.

record_episode ~76

Record a transfer episode for a node pair. Increments episode count toward VLA training threshold.

NameTypeReqDescription
episodeIdstring–Episode ID (optional)
fromNodeIdstringyesSource instrument node ID
successboolean–Whether the episode succeeded
toNodeIdstringyesDestination instrument node ID

No output schema declared.

No examples provided.

redeem_invite ~82

One-click agent onboarding with an invite code. Provisions wallet, identity, LLM access, and PCC tools in a single call.

NameTypeReqDescription
emailstringyesEmail address for the account
inviteCodestringyesInvite code to redeem
namestring–Display name (optional)
passwordstringyesPassword for the account

No output schema declared.

No examples provided.

register_capability_ip ~113

Register a capability as a Story Protocol IP Asset. Returns an ipId and NFT token. The designer earns royalties whenever this capability is used.

NameTypeReqDescription
capabilityobjectyesCapability object
commercialRevSharenumber–Revenue share percentage for commercial use (0-100)
designerAddressstringyesEVM address of the capability designer
designerNamestringyesDisplay name of the designer
ipfsCidstring–IPFS CID of the capability spec document (optional)

No output schema declared.

No examples provided.

register_job_evidence_ip ~128

Register job evidence as a derivative IP asset on Story Protocol, linking it to the parent capability's IP. Operators earn royalties from derivative use.

NameTypeReqDescription
evidenceBundleHashstringyesHash of the evidence bundle
ipfsCidstring–IPFS CID of the evidence bundle (optional)
jobIdstringyesJob ID whose evidence is being registered
operatorAddressstringyesEVM address of the operator
operatorNamestringyesDisplay name of the operator
parentIpIdstringyesIP ID of the parent capability

No output schema declared.

No examples provided.

reject_registration ~47

Reject a machine registration with a reason. The operator can see the rejection reason and resubmit.

NameTypeReqDescription
reasonstring–Reason for rejection
registrationIdstringyesRegistration ID

No output schema declared.

No examples provided.

release_milestone ~57

Release a milestone payment on-chain after the challenge window has expired. Returns transaction hash.

NameTypeReqDescription
addressstringyesEscrow contract address (0x...)
milestoneIndexnumberyesMilestone index to release (0-based)

No output schema declared.

No examples provided.

render_pcc_dashboard ~103

Compose a live PCC dashboard for a physical-capability task — pass a DashboardManifest (windows + live data bindings + actions) and it renders as an interactive MCP App.

NameTypeReqDescription
api_basestring–Gateway base URL. Default https://capability.network.
csd–yesThe builtin CSD URI this manifest conforms to.
descriptionstring––
sectionsarrayyes–
theme–––
titlestringyes–
NameTypeReqDescription
manifestobjectyes–

No examples provided.

render_pcc_dashboard_ir ~108

Compose a live PCC dashboard rendered through the closed, PCC-owned IR (read-only). Pass a DashboardManifest; it renders as an interactive MCP App via the audited closed-IR render path.

NameTypeReqDescription
api_basestring–Gateway base URL. Default https://capability.network.
csd–yesThe builtin CSD URI this manifest conforms to.
descriptionstring––
sectionsarrayyes–
theme–––
titlestringyes–
NameTypeReqDescription
manifestobjectyes–

No examples provided.

reply_to_support_thread ~84

Reply to an existing support thread. Use when the operator wants to add information to a thread started earlier. Needs the threadId from check_support_replies or the original send_support_message response.

NameTypeReqDescription
messagestringyesReply message
retrievalCodestring–Optional diagnostic retrieval code to attach
threadIdstringyesThread ID to reply to

No output schema declared.

No examples provided.

report_anomaly ~99

Report a detected anomaly — protocol failure, evidence mismatch, stuck job, or suspicious behavior. All agents on the network are notified.

NameTypeReqDescription
categorystringyesAnomaly category
descriptionstringyesHuman-readable description of what went wrong
jobIdstring–Related job ID (optional)
severitystringyesAnomaly severity
targetAgentIdstring–Agent or kernel ID being reported (optional)

No output schema declared.

No examples provided.

report_protocol_failure ~108

Report a protocol failure — when a step in the evidence/escrow/verification pipeline breaks. System may auto-recover.

NameTypeReqDescription
errorCodestringyesError code
errorMessagestringyesError description
involvedAgentsarrayyesAgent IDs involved
jobIdstring–Related job ID
protocolstringyesWhich protocol failed: evidence_submission, escrow_release, verification_consensus, settlement
recoveryActionstring–Suggested recovery

No output schema declared.

No examples provided.

resolve_anomaly ~44

Mark an anomaly as resolved with a resolution note.

NameTypeReqDescription
anomalyIdstringyesAnomaly ID to resolve
resolutionstringyesHow the anomaly was resolved

No output schema declared.

No examples provided.

respond_to_verification ~90

Submit a verifier's verdict for a verification request. Returns consensus state after this vote.

NameTypeReqDescription
notesstring–Optional notes explaining the verdict
requestIdstringyesVerification request ID (hvreq_...)
signaturestringyesCryptographic signature of the verdict
verdictstringyesVerifier's verdict
verifierIdstringyesVerifier node ID

No output schema declared.

No examples provided.

resume_protocol_run ~32

Resume a paused protocol run from where it stopped.

NameTypeReqDescription
runIdstringyesProtocol run ID to resume

No output schema declared.

No examples provided.

retrieve_ipfs ~41

Retrieve raw data from IPFS by CID. Used to fetch archived evidence bundles from decentralized storage.

NameTypeReqDescription
cidstringyesIPFS content identifier (CID)

No output schema declared.

No examples provided.

revoke_api_key ~56

Revoke an API key permanently. The key will immediately stop working. You must own the key. Use list_api_keys to find the key ID.

NameTypeReqDescription
keyIdstringyesKey ID to revoke (from list_api_keys)

No output schema declared.

No examples provided.

save_dashboard ~538

Save a generated dashboard to the network so the user gets a live, shareable URL: https://capability.network/a/<slug>. Pass a `manifest` — a small declarative DashboardManifest (windows + live-data bindings + actions) conforming to the schema at https://capability.network/ui-kit/v1/manifest.schema.json; the shipped pcc-ui kit renders it identically everywhere (you compose the manifest, the kit renders it — never hand-rolled HTML). WHEN to call this: only when the task needs a surface to watch/approve/compare/reuse (a live job, a value chain, a settlement trail, a recurring order) — never for a one-line answer. RECALL FIRST: call search_dashboards before generating; reload or fork a match instead of duplicating. The manifest MUST NOT contain an API key (a shared artifact travels with its contents — the network rejects one that does). Returns the stored artifact incl. its slug. Defaults visibility to 'unlisted' (link-shareable, not listed).

NameTypeReqDescription
capabilityTypesarray–Capability types this dashboard is about, e.g. ['pizza.order','courier.dispatch']. This is the discovery join — it's how search_dashboards finds this artifact later.
composeRefsarray–Optional pinned, re-plannable ComposeRequest objects (value chains). Pin the request, never a compositionId (those expire in 30 min).
descriptionstring–One-line description of what the dashboard shows.
manifestobjectyesThe DashboardManifest (2-6KB JSON) conforming to https://capability.network/ui-kit/v1/manifest.schema.json. Required top-level keys: `csd` (must be 'pcc://artifacts/dashboard/v1'), `title`, and `sect…
namestringyesShort human name for the dashboard, e.g. 'Watch my pizza + courier'. Used to mint the slug.
renderedCidstring–Optional CID of a rendered-HTML export saved via /api/storage.
visibilitystring–Who can load it. Default 'unlisted' (anyone with the link; not in listings). 'public' appears in search_dashboards; 'private' is owner-only.
NameTypeReqDescription
manifestobjectyes–
namestring––
slugstring––

No examples provided.

search_capabilities ~46

Search capability templates by type or keyword. Returns templates with pricing, assurance tiers, and availability.

NameTypeReqDescription
querystringyesSearch query (type name, material, process, etc.)

No output schema declared.

No examples provided.

search_dashboards ~203

Discover existing public dashboards before you generate a new one (recall-first — the library accrues; adopt > extend > build for UIs too). Filter by `capabilityType` (e.g. 'pizza.order'), free-text `q` over name/description/types, and `sort` by popularity or recency. Returns { entries, total, offset, limit }. Only public artifacts are listed; unlisted ones load by slug via get_dashboard but never appear here.

NameTypeReqDescription
capabilityTypestring–Filter to dashboards tagged with this capability type, e.g. 'pizza.order'.
limitinteger–Max results (1..100, default 20).
offsetinteger–Pagination offset (default 0).
qstring–Free-text search over name, description, and capability types.
sortstring–Ranking: 'popular' (by use+load+fork counts) or 'recent' (default).
NameTypeReqDescription
entriesarrayyes–
totalnumber––

No examples provided.

search_spaces ~57

Search for lab/workshop hosting spaces. Filter by size, access schedule, and other requirements.

NameTypeReqDescription
accessstring–Access schedule (24/7, business-hours, all)
maxSqftnumber–Maximum square footage

No output schema declared.

No examples provided.

send_diagnostics ~205

Upload an encrypted diagnostic bundle when the operator's node has problems. The bundle is encrypted client-side with a retrieval code the operator must share with support before logs can be read. Use this when the operator reports errors, crashes, or misbehavior. The pcc-node CLI runs `pcc-node logs --send` locally to collect+encrypt; prefer that path when available. This tool is for agent-driven uploads when the bundle is already prepared.

NameTypeReqDescription
bundleHashstring–sha256 of plaintext bundle
bundleSizenumber–Size of encrypted payload in bytes
collectedAtstring–ISO timestamp when bundle was collected
encryptedobjectyesEncrypted bundle payload
kernelIdstringyesKernel ID the diagnostics came from
logLineCountnumber–How many log lines are in the bundle
systemPlatformstring–e.g. Linux-5.15, Darwin-23, Windows-10

No output schema declared.

No examples provided.

send_support_message ~186

Send an operator support message to the PCC team. Creates a new support thread or appends to the operator's existing open thread. Can optionally attach a diagnostic retrieval code (from send_diagnostics) so support staff can decrypt logs. Discord webhook fires on every new message, so expect fast response. Use this whenever the operator says something is broken, confusing, or not behaving as expected.

NameTypeReqDescription
kernelIdstringyesOperator's kernel ID
kernelNamestring–Human-readable kernel name
messagestringyesThe support message text — describe the problem concretely
retrievalCodestring–Optional diagnostic retrieval code to attach (from send_diagnostics)
subjectstring–Optional thread subject (auto-generated from message if omitted)
systemInfoobject–Optional system context (platform, nodeVersion, daemonRunning, gatewayReachable)

No output schema declared.

No examples provided.

setup_detect ~41

Auto-detect current setup state: env vars, database, adapters, chain connectivity, storage, identity. Use this to see what's configured and what's missing before onboarding.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

setup_generate_config ~56

Generate a KERNEL_CONFIG JSON from device descriptions. Tell it what machines you have and it produces the config ready to paste into your environment.

NameTypeReqDescription
devicesarrayyesArray of device descriptions with type, model, and connection info

No output schema declared.

No examples provided.

setup_register_device ~198

Register a device in the database with adapter config and capabilities. Part of Step 3 in the onboarding flow. Required: kernelId, deviceId, type and adapterType (400 missing_required_fields otherwise).

NameTypeReqDescription
adapterConfigobject–Adapter-specific configuration (host, port, auth, etc.)
adapterTypestringyesOne of octoprint, modbus, opcua, sila, ipp, generic-http or mock; the route refuses anything else (including opentrons)
capabilitiesarray–Capability types this device serves
deviceIdstringyesYour ID for this device, unique within the kernel
kernelIdstringyesKernel ID to register the device under
modelstring–Device model identifier (optional; stored as "unknown" if absent)
typestringyesDevice role: machine, sensor or camera (the values setup_generate_config and setup_validate accept)

No output schema declared.

No examples provided.

setup_status ~38

Comprehensive setup status across 6 categories: gateway, database, adapters, chain, storage, identity. Use to confirm everything is green before going live.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

setup_test_job ~62

Submit a test job to verify the full pipeline works end-to-end (Step 4 of onboarding). Returns job ID and result.

NameTypeReqDescription
deviceIdstring–Specific device ID to test (optional)
kernelIdstringyesKernel ID to test

No output schema declared.

No examples provided.

setup_validate ~44

Validate a kernel config (20+ checks: JSON structure, device connectivity, adapter compatibility). Returns validation errors and warnings.

NameTypeReqDescription
configobjectyesKernel config JSON to validate

No output schema declared.

No examples provided.

stake_in_pool ~56

Stake USDC or credits into a capability investment pool.

NameTypeReqDescription
amountnumberyesAmount to stake
poolIdstringyesInvestment pool ID
stakerstringyesAddress or DID of the staker

No output schema declared.

No examples provided.

start_protocol_run ~40

Start execution of a protocol run that is in 'ready' or 'binding' state.

NameTypeReqDescription
runIdstringyesProtocol run ID to start

No output schema declared.

No examples provided.

submit_attestation ~90

Submit a verifier attestation for a milestone on-chain. Used by third-party verifiers (Bittensor subnet) to confirm evidence quality. Returns transaction hash.

NameTypeReqDescription
addressstringyesEscrow contract address (0x...)
attestationHashstringyesAttestation hash as 0x-prefixed hex bytes32
milestoneIndexnumberyesMilestone index (0-based)

No output schema declared.

No examples provided.

submit_demand ~133

Signal that you want a capability that doesn't exist on the network yet. Creates a demand signal and may auto-create a bounty if enough demand accumulates.

NameTypeReqDescription
assuranceTiernumber–Required assurance tier (0-3)
capabilityTypestringyesType of capability wanted (e.g. electron-beam-welding, cryo-em)
descriptionstringyesDescription of what you need
estimatedFrequencystring–How often you would use this capability
estimatedJobValuenumber–Estimated payment per job in USD
requesterIdstringyesID of the requester

No output schema declared.

No examples provided.

submit_evidence_hash ~85

Submit an evidence bundle hash for a milestone on-chain. Links the physical evidence to the on-chain settlement record. Returns transaction hash.

NameTypeReqDescription
addressstringyesEscrow contract address (0x...)
evidenceBundleHashstringyesEvidence bundle hash as 0x-prefixed hex bytes32
milestoneIndexnumberyesMilestone index (0-based)

No output schema declared.

No examples provided.

submit_feedback ~61

Submit a bug report, suggestion, or general feedback about the PCC network.

NameTypeReqDescription
messagestringyesFeedback message (max 5000 chars)
pagestring–Page or feature the feedback relates to
typestring–Feedback type

No output schema declared.

No examples provided.

submit_for_human_verification ~120

Submit an evidence bundle for human verification. Selects a panel of verifiers from the network and returns assigned verifier IDs.

NameTypeReqDescription
bundleHashstringyesSHA-256 hash of the evidence bundle
comparisonScorenumber–Pre-computed comparison score 0-1 (optional)
photoRefstringyesReference to the photo evidence (CID or URL)
referenceRefstringyesReference to the reference/spec document
verifierCountnumber–Number of verifiers to assign (default 5)

No output schema declared.

No examples provided.

suggest_csd_templates ~183

Bidirectional onboarding: the registry talks back. Describe in plain English what you are trying to set up — 'wood-fired pizza shop in SF', 'Opentrons OT-2 liquid handler', 'same-day SF courier' — and the registry returns N candidate Capability StructureDefinition (CSD) templates ranked by keyword-overlap relevance (name×3, tags×2, description×1; tie-break on usage). Empty query falls back to popularity-ordered top picks. After picking one, pass the chosen type to pcc-author-integration. Score-zero results are dropped.

NameTypeReqDescription
kindstring–Filter by CSD kind.
limitinteger–Max results (1..20, default 5).
qstring–Plain-English description of the capability the user is trying to set up. Optional — empty falls back to popularity.

No output schema declared.

No examples provided.

system_telemetry ~44

Raw system state dump — actual DB rows for kernels, devices, jobs, evidence, registrations, capabilities, agent conversations, audit log. No fake numbers, no summaries.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

test_operator_channels ~65

Fire a synthetic job at every enabled channel for an operator so the onboarding agent (and the human watching) can confirm the integration end-to-end before a real job lands. Returns per-channel dispatch results (delivered, ref, warnings).

NameTypeReqDescription
slugstringyesOperator slug.

No output schema declared.

No examples provided.

update_dashboard ~212

Modify a dashboard you own (owner-only). Replace the manifest or any metadata field; the version increments. Use this to edit a saved surface meaningfully — 'raise budgetUSD to 40', 'add a receipt window', 'make it public'. A replaced manifest must still conform to the schema and must not contain an API key. Only send the fields you want to change.

NameTypeReqDescription
capabilityTypesarray–Replacement capability-type tags.
composeRefsarray–Replacement pinned ComposeRequest objects.
descriptionstring–New description.
idstringyesThe id (ua_...) of the artifact to update.
manifestobject–Replacement DashboardManifest (must conform to the schema; no API key). Omit to leave the manifest unchanged.
namestring–New name.
renderedCidstring–New rendered-HTML export CID.
visibilitystring–New visibility (e.g. flip 'unlisted' -> 'public' to list it).
NameTypeReqDescription
manifestobjectyes–
namestring––
slugstring––

No examples provided.

Install

How do I install the Physical Capability Cloud MCP server?

Physical Capability Cloud is a hosted endpoint at https://capability.network/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · capability.network

# add to Claude Code
claude mcp add --transport http network-capability-physical-capability-cloud 'https://capability.network/mcp'
Common questions

What is the Physical Capability Cloud MCP server?

Physical Capability Cloud is an MCP server listed in the public MCP registry as network.capability/physical-capability-cloud. Discover, hire, and verify real-world physical capability through MCP. This page covers its hosted endpoint (https://capability.network/mcp).

Is the Physical Capability Cloud MCP server safe to use?

Physical Capability Cloud scores 79 out of 100 on VerifyMCP. 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 Physical Capability Cloud MCP server expose?

Physical Capability Cloud exposes 256 tools: provision_api_key, list_api_keys, revoke_api_key, setup_detect, setup_generate_config, and 251 more. Their descriptions and schemas cost roughly 22,670 tokens of context every time the server is loaded.

Does the Physical Capability Cloud MCP server require authentication?

No. We connected to Physical Capability Cloud without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Physical Capability Cloud MCP server still maintained?

Physical Capability Cloud is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Physical Capability Cloud MCP server?

VerifyMCP ran 14 checks on Physical Capability Cloud, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.