AnyDB MCP integration for AI agents.
Connect AI agents to AnyDB through 7 structured actions, including get record, create record, and list databases. Review authentication, inputs, workflows, a…
- ACTION CONTRACTS
- 7
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the AnyDB integration exposes
The AnyDB Agent App exposes 7 provider-backed actions for data and productivity work. Its current contract lets an authorized agent get one anydb record with its metadata and cell content, create a structured record in an anydb database, and list the anydb databases in a team. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected AnyDB account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real AnyDB capabilities.
Showing 7 of 7 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_recordREADGet one AnyDB record with its metadata and cell content.
INPUTS: teamid / adbid / adoid
create_recordWRITECreate a structured record in an AnyDB database.
INPUTS: teamid / adbid / name / attach / template
list_databasesREADList the AnyDB databases in a team.
INPUTS: teamid
list_recordsREADList records in an AnyDB database with cursor pagination and optional hierarchy filters.
INPUTS: teamid / adbid / parentid / templateid / templatename
list_teamsREADList the AnyDB teams accessible to the connected account.
search_recordsREADSearch records in an AnyDB database by keyword.
INPUTS: teamid / adbid / search / limit
update_recordWRITEUpdate the metadata or cell content of an AnyDB record.
INPUTS: meta / content
INPUT CONTRACTS
Know what the action needs before it runs.
get_record
teamidOPTIONAL- The AnyDB team identifier.
adbidOPTIONAL- The AnyDB database identifier.
adoidOPTIONAL- The AnyDB record identifier.
create_record
teamidREQUIRED- The AnyDB team identifier.
adbidREQUIRED- The AnyDB database identifier.
nameREQUIRED- The display name of the new record.
attachOPTIONAL- An optional parent record identifier to attach the new record to.
templateOPTIONAL- An optional AnyDB template identifier.
list_databases
teamidOPTIONAL- The AnyDB team identifier.
list_records
teamidREQUIRED- The AnyDB team identifier.
adbidREQUIRED- The AnyDB database identifier.
parentidOPTIONAL- An optional parent record identifier used to list children.
templateidOPTIONAL- An optional template identifier used to filter records.
templatenameOPTIONAL- An optional template name used to filter records.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Record
Get one AnyDB record with its metadata and cell content. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_recordControl Create Record
Create a structured record in an AnyDB database. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_recordVerify with List Databases
List the AnyDB databases in a team. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_databasesSAFETY BOUNDARY
Operate AnyDB with explicit limits
- Authorize AnyDB with API key and grant only the provider access required by the selected actions.
- 2 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in AnyDB rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the AnyDB task completed successfully.
CONNECTION MODEL
API key
AnyDB API key sent in the x-anydb-api-key header. Copy it from the Integration tab in your AnyDB profile: https://www.anydb.com/support/integrations/typescript-sdk/.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 5
- WRITE SIGNALS
- 2
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by AnyDB.