fec_candidate_search
Search federal candidates (President, House, Senate) by name, state, office, or party using FEC data. Returns candidate IDs needed for the other FEC tools.
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/fec-candidate-search.md
What fec_candidate_search does on Livedatalink
AI agents call fec_candidate_search to retrieve information from Livedatalink without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
cycle | number | — | Two-year election cycle (even year, e.g. 2024). Optional. |
limit | number | — | Maximum candidates to return (default 20, max 100). |
party | string | — | Party code (e.g. 'DEM', 'REP', 'IND', 'LIB'). Optional. |
query | string | — | Candidate name fragment (e.g. 'Warren', 'Smith'). Optional. |
state | string | — | Two-letter state code to filter by (e.g. 'MA', 'TX'). Optional. |
office | string | — | Office: 'P' (President), 'S' (Senate), or 'H' (House). Optional. |
Parameters from the server's own tool schema.
Why fec_candidate_search is rated Low
This is a search/lookup function over public Federal Election Commission data. It retrieves candidate information based on filter criteria and returns identifiers. No data is created, modified, deleted, or used to move money or execute arbitrary operations. The blast radius of misuse is minimal since FEC candidate data is public record.
From the tool's definition The tool 'Search federal candidates...by name, state, office, or party using FEC data. Returns candidate IDs' performs a query operation that retrieves publicly available information without modifying data or triggering external actions.
Attacks that exploit this kind of access
The rule that runs fec_candidate_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fec_candidate_search, this is the rule to start with:
fec_candidate_search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every fec_candidate_search call is checked against it from then on.
Questions about fec_candidate_search
Search federal candidates (President, House, Senate) by name, state, office, or party using FEC data. Returns candidate IDs needed for the other FEC tools. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
fec_candidate_search accepts 6 parameters: cycle, limit, party, query, state, office. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for fec_candidate_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Livedatalink. Nothing to install.
fec_candidate_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fec_candidate_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for fec_candidate_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fec_candidate_search is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue